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

@@ -15,6 +15,20 @@ HOST=localhost
 PORT=3080
 
 MONGO_URI=mongodb://127.0.0.1:27017/LibreChat
+#The maximum number of connections in the connection pool. */
+MONGO_MAX_POOL_SIZE=
+#The minimum number of connections in the connection pool. */
+MONGO_MIN_POOL_SIZE=
+#The maximum number of connections that may be in the process of being established concurrently by the connection pool. */
+MONGO_MAX_CONNECTING=
+#The maximum number of milliseconds that a connection can remain idle in the pool before being removed and closed. */
+MONGO_MAX_IDLE_TIME_MS=
+#The maximum time in milliseconds that a thread can wait for a connection to become available. */
+MONGO_WAIT_QUEUE_TIMEOUT_MS=
+# Set to false to disable automatic index creation for all models associated with this connection. */
+MONGO_AUTO_INDEX=
+# Set to `false` to disable Mongoose automatically calling `createCollection()` on every model created on this connection. */
+MONGO_AUTO_CREATE=
 
 DOMAIN_CLIENT=http://localhost:3080
 DOMAIN_SERVER=http://localhost:3080
@@ -26,6 +40,13 @@ NO_INDEX=true
 # Defaulted to 1.
 TRUST_PROXY=1
 
+# Minimum password length for user authentication
+# Default: 8
+# Note: When using LDAP authentication, you may want to set this to 1 
+# to bypass local password validation, as LDAP servers handle their own
+# password policies.
+# MIN_PASSWORD_LENGTH=8
+
 #===============#
 # JSON Logging  #
 #===============#
@@ -142,10 +163,10 @@ GOOGLE_KEY=user_provided
 # GOOGLE_AUTH_HEADER=true
 
 # Gemini API (AI Studio)
-# GOOGLE_MODELS=gemini-2.5-pro,gemini-2.5-flash,gemini-2.5-flash-lite-preview-06-17,gemini-2.0-flash,gemini-2.0-flash-lite
+# GOOGLE_MODELS=gemini-2.5-pro,gemini-2.5-flash,gemini-2.5-flash-lite,gemini-2.0-flash,gemini-2.0-flash-lite
 
 # Vertex AI
-# GOOGLE_MODELS=gemini-2.5-pro,gemini-2.5-flash,gemini-2.5-flash-lite-preview-06-17,gemini-2.0-flash-001,gemini-2.0-flash-lite-001
+# GOOGLE_MODELS=gemini-2.5-pro,gemini-2.5-flash,gemini-2.5-flash-lite,gemini-2.0-flash-001,gemini-2.0-flash-lite-001
 
 # GOOGLE_TITLE_MODEL=gemini-2.0-flash-lite-001
 
@@ -175,7 +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
 
@@ -233,6 +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
@@ -349,6 +374,11 @@ REGISTRATION_VIOLATION_SCORE=1
 CONCURRENT_VIOLATION_SCORE=1
 MESSAGE_VIOLATION_SCORE=1
 NON_BROWSER_VIOLATION_SCORE=20
+TTS_VIOLATION_SCORE=0
+STT_VIOLATION_SCORE=0
+FORK_VIOLATION_SCORE=0
+IMPORT_VIOLATION_SCORE=0
+FILE_UPLOAD_VIOLATION_SCORE=0
 
 LOGIN_MAX=7
 LOGIN_WINDOW=5
@@ -433,10 +463,15 @@ 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
 OPENID_NAME_CLAIM=
+# Optional audience parameter for OpenID authorization requests
+OPENID_AUDIENCE=
 
 OPENID_BUTTON_LABEL=
 OPENID_IMAGE_URL=
@@ -453,11 +488,26 @@ OPENID_REUSE_TOKENS=
 OPENID_JWKS_URL_CACHE_ENABLED=
 OPENID_JWKS_URL_CACHE_TIME= # 600000 ms eq to 10 minutes leave empty to disable caching
 #Set to true to trigger token exchange flow to acquire access token for the userinfo endpoint.
-OPENID_ON_BEHALF_FLOW_FOR_USERINFRO_REQUIRED=
-OPENID_ON_BEHALF_FLOW_USERINFRO_SCOPE = "user.read" # example for Scope Needed for Microsoft Graph API
+OPENID_ON_BEHALF_FLOW_FOR_USERINFO_REQUIRED=
+OPENID_ON_BEHALF_FLOW_USERINFO_SCOPE="user.read" # example for Scope Needed for Microsoft Graph API
 # Set to true to use the OpenID Connect end session endpoint for logout
 OPENID_USE_END_SESSION_ENDPOINT=
 
+#========================#
+# SharePoint Integration #
+#========================#
+# Requires Entra ID (OpenID) authentication to be configured
+
+# Enable SharePoint file picker in chat and agent panels
+# ENABLE_SHAREPOINT_FILEPICKER=true
+
+# SharePoint tenant base URL (e.g., https://yourtenant.sharepoint.com)
+# SHAREPOINT_BASE_URL=https://yourtenant.sharepoint.com
+
+# Microsoft Graph API And SharePoint scopes for file picker
+# SHAREPOINT_PICKER_SHAREPOINT_SCOPE==https://yourtenant.sharepoint.com/AllSites.Read
+# SHAREPOINT_PICKER_GRAPH_SCOPE=Files.Read.All
+#========================#
 
 # SAML
 # Note: If OpenID is enabled, SAML authentication will be automatically disabled.
@@ -485,6 +535,21 @@ SAML_IMAGE_URL=
 # SAML_USE_AUTHN_RESPONSE_SIGNED=
 
 
+#===============================================#
+# Microsoft Graph API / Entra ID Integration  #
+#===============================================#
+
+# Enable Entra ID people search integration in permissions/sharing system
+# When enabled, the people picker will search both local database and Entra ID
+USE_ENTRA_ID_FOR_PEOPLE_SEARCH=false
+
+# When enabled, entra id groups owners will be considered as members of the group
+ENTRA_ID_INCLUDE_OWNERS_AS_MEMBERS=false
+
+# Microsoft Graph API scopes needed for people/group search
+# Default scopes provide access to user profiles and group memberships
+OPENID_GRAPH_SCOPES=User.Read,People.Read,GroupMember.Read.All
+
 # LDAP
 LDAP_URL=
 LDAP_BIND_DN=
@@ -575,6 +640,10 @@ ALLOW_SHARED_LINKS_PUBLIC=true
 # If you have another service in front of your LibreChat doing compression, disable express based compression here
 # DISABLE_COMPRESSION=true
 
+# If you have gzipped version of uploaded image images in the same folder, this will enable gzip scan and serving of these images
+# Note: The images folder will be scanned on startup and a ma kept in memory. Be careful for large number of images.
+# ENABLE_IMAGE_OUTPUT_GZIP_SCAN=true
+
 #===================================================#
 #                        UI                         #
 #===================================================#
@@ -588,15 +657,64 @@ 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 #
 #===============#
 
-# REDIS_URI=10.10.10.10:6379
+# Enable Redis for caching and session storage
 # USE_REDIS=true
 
-# USE_REDIS_CLUSTER=true
-# REDIS_CA=/path/to/ca.crt
+# Single Redis instance
+# REDIS_URI=redis://127.0.0.1:6379
+
+# Redis cluster (multiple nodes)
+# REDIS_URI=redis://127.0.0.1:7001,redis://127.0.0.1:7002,redis://127.0.0.1:7003
+
+# Redis with TLS/SSL encryption and CA certificate
+# REDIS_URI=rediss://127.0.0.1:6380
+# REDIS_CA=/path/to/ca-cert.pem
+
+# Elasticache may need to use an alternate dnsLookup for TLS connections.  see "Special Note: Aws Elasticache Clusters with TLS" on this webpage: https://www.npmjs.com/package/ioredis
+# Enable alternative dnsLookup for redis
+# REDIS_USE_ALTERNATIVE_DNS_LOOKUP=true
+
+# Redis authentication (if required)
+# REDIS_USERNAME=your_redis_username
+# REDIS_PASSWORD=your_redis_password
+
+# Redis key prefix configuration
+# Use environment variable name for dynamic prefix (recommended for cloud deployments)
+# REDIS_KEY_PREFIX_VAR=K_REVISION
+# Or use static prefix directly
+# REDIS_KEY_PREFIX=librechat
+
+# Redis connection limits
+# REDIS_MAX_LISTENERS=40
+
+# Redis ping interval in seconds (0 = disabled, >0 = enabled)
+# When set to a positive integer, Redis clients will ping the server at this interval to keep connections alive
+# When unset or 0, no pinging is performed (recommended for most use cases)
+# REDIS_PING_INTERVAL=300
+
+# Force specific cache namespaces to use in-memory storage even when Redis is enabled
+# 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                      #
@@ -658,3 +776,16 @@ OPENWEATHER_API_KEY=
 # JINA_API_KEY=your_jina_api_key
 # or
 # COHERE_API_KEY=your_cohere_api_key
+
+#======================#
+# MCP Configuration    #
+#======================#
+
+# Treat 401/403 responses as OAuth requirement when no oauth metadata found
+# MCP_OAUTH_ON_AUTH_ERROR=true
+
+# Timeout for OAuth detection requests in milliseconds
+# MCP_OAUTH_DETECTION_TIMEOUT=5000
+
+# Cache connection status checks for this many milliseconds to avoid expensive verification
+# MCP_CONNECTION_CHECK_TTL=60000

.github/CONTRIBUTING.md

@@ -147,7 +147,7 @@ Apply the following naming conventions to branches, labels, and other Git-relate
 ## 8. Module Import Conventions
 
 - `npm` packages first, 
-     - from shortest line (top) to longest (bottom)
+     - from longest line (top) to shortest (bottom)
 
 - Followed by typescript types (pertains to data-provider and client workspaces)
      - longest line (top) to shortest (bottom)
@@ -157,6 +157,8 @@ Apply the following naming conventions to branches, labels, and other Git-relate
      - longest line (top) to shortest (bottom)
      - imports with alias `~` treated the same as relative import with respect to line length
 
+**Note:** ESLint will automatically enforce these import conventions when you run `npm run lint --fix` or through pre-commit hooks.
+
 ---
 
 Please ensure that you adapt this summary to fit the specific context and nuances of your project.

.github/workflows/backend-review.yml

@@ -7,7 +7,7 @@ on:
       - release/*
     paths:
       - 'api/**'
-      - 'packages/api/**'
+      - 'packages/**'
 jobs:
   tests_Backend:
     name: Run Backend unit tests

.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

.github/workflows/client.yml

@@ -0,0 +1,58 @@
+name: Publish `@librechat/client` to NPM
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - 'packages/client/package.json'
+  workflow_dispatch:
+    inputs:
+      reason:
+        description: 'Reason for manual trigger'
+        required: false
+        default: 'Manual publish requested'
+
+jobs:
+  build-and-publish:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      
+      - name: Use Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '20.x'
+        
+      - name: Install client dependencies
+        run: cd packages/client && npm ci
+        
+      - name: Build client
+        run: cd packages/client && npm run build
+        
+      - name: Set up npm authentication
+        run: echo "//registry.npmjs.org/:_authToken=${{ secrets.PUBLISH_NPM_TOKEN }}" > ~/.npmrc
+        
+      - name: Check version change
+        id: check
+        working-directory: packages/client
+        run: |
+          PACKAGE_VERSION=$(node -p "require('./package.json').version")
+          PUBLISHED_VERSION=$(npm view @librechat/client version 2>/dev/null || echo "0.0.0")
+          if [ "$PACKAGE_VERSION" = "$PUBLISHED_VERSION" ]; then
+            echo "No version change, skipping publish"
+            echo "skip=true" >> $GITHUB_OUTPUT
+          else
+            echo "Version changed, proceeding with publish"
+            echo "skip=false" >> $GITHUB_OUTPUT
+          fi
+            
+      - name: Pack package
+        if: steps.check.outputs.skip != 'true'
+        working-directory: packages/client
+        run: npm pack
+        
+      - name: Publish
+        if: steps.check.outputs.skip != 'true'
+        working-directory: packages/client
+        run: npm publish *.tgz --access public

.github/workflows/data-provider.yml

@@ -1,4 +1,4 @@
-name: Node.js Package
+name: Publish `librechat-data-provider` to NPM
 
 on:
   push:
@@ -6,6 +6,12 @@ on:
       - main
     paths:
       - 'packages/data-provider/package.json'
+  workflow_dispatch:
+    inputs:
+      reason:
+        description: 'Reason for manual trigger'
+        required: false
+        default: 'Manual publish requested'
 
 jobs:
   build:
@@ -14,7 +20,7 @@ jobs:
       - uses: actions/checkout@v4
       - uses: actions/setup-node@v4
         with:
-          node-version: 16
+          node-version: 20
       - run: cd packages/data-provider && npm ci
       - run: cd packages/data-provider && npm run build
 
@@ -25,7 +31,7 @@ jobs:
       - uses: actions/checkout@v4
       - uses: actions/setup-node@v4
         with:
-          node-version: 16
+          node-version: 20
           registry-url: 'https://registry.npmjs.org'
       - run: cd packages/data-provider && npm ci
       - run: cd packages/data-provider && npm run build

.github/workflows/data-schemas.yml

@@ -22,7 +22,7 @@ jobs:
       - name: Use Node.js
         uses: actions/setup-node@v4
         with:
-          node-version: '18.x'
+          node-version: '20.x'
           
       - name: Install dependencies
         run: cd packages/data-schemas && npm ci

.github/workflows/frontend-review.yml

@@ -8,7 +8,7 @@ on:
       - release/*
     paths:
       - 'client/**'
-      - 'packages/**'
+      - 'packages/data-provider/**'
 
 jobs:
   tests_frontend_ubuntu:

.github/workflows/generate-release-changelog-pr.yml

@@ -1,95 +0,0 @@
-name: Generate Release Changelog PR
-
-on:
-  push:
-    tags:
-      - 'v*.*.*'
-  workflow_dispatch:
-
-jobs:
-  generate-release-changelog-pr:
-    permissions:
-      contents: write    # Needed for pushing commits and creating branches.
-      pull-requests: write
-    runs-on: ubuntu-latest
-    steps:
-      # 1. Checkout the repository (with full history).
-      - name: Checkout Repository
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      # 2. Generate the release changelog using our custom configuration.
-      - name: Generate Release Changelog
-        id: generate_release
-        uses: mikepenz/release-changelog-builder-action@v5.1.0
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          configuration: ".github/configuration-release.json"
-          owner: ${{ github.repository_owner }}
-          repo: ${{ github.event.repository.name }}
-          outputFile: CHANGELOG-release.md
-
-      # 3. Update the main CHANGELOG.md:
-      #    - If it doesn't exist, create it with a basic header.
-      #    - Remove the "Unreleased" section (if present).
-      #    - Prepend the new release changelog above previous releases.
-      #    - Remove all temporary files before committing.
-      - name: Update CHANGELOG.md
-        run: |
-          # Determine the release tag, e.g. "v1.2.3"
-          TAG=${GITHUB_REF##*/}
-          echo "Using release tag: $TAG"
-          
-          # Ensure CHANGELOG.md exists; if not, create a basic header.
-          if [ ! -f CHANGELOG.md ]; then
-            echo "# Changelog" > CHANGELOG.md
-            echo "" >> CHANGELOG.md
-            echo "All notable changes to this project will be documented in this file." >> CHANGELOG.md
-            echo "" >> CHANGELOG.md
-          fi
-
-          echo "Updating CHANGELOG.md…"
-          
-          # Remove the "Unreleased" section (from "## [Unreleased]" until the first occurrence of '---') if it exists.
-          if grep -q "^## \[Unreleased\]" CHANGELOG.md; then
-            awk '/^## \[Unreleased\]/{flag=1} flag && /^---/{flag=0; next} !flag' CHANGELOG.md > CHANGELOG.cleaned
-          else
-            cp CHANGELOG.md CHANGELOG.cleaned
-          fi
-
-          # Split the cleaned file into:
-          #   - header.md: content before the first release header ("## [v...").
-          #   - tail.md: content from the first release header onward.
-          awk '/^## \[v/{exit} {print}' CHANGELOG.cleaned > header.md
-          awk 'f{print} /^## \[v/{f=1; print}' CHANGELOG.cleaned > tail.md
-
-          # Combine header, the new release changelog, and the tail.
-          echo "Combining updated changelog parts..."
-          cat header.md CHANGELOG-release.md > CHANGELOG.md.new
-          echo "" >> CHANGELOG.md.new
-          cat tail.md >> CHANGELOG.md.new
-
-          mv CHANGELOG.md.new CHANGELOG.md
-
-          # Remove temporary files.
-          rm -f CHANGELOG.cleaned header.md tail.md CHANGELOG-release.md
-
-          echo "Final CHANGELOG.md content:"
-          cat CHANGELOG.md
-
-      # 4. Create (or update) the Pull Request with the updated CHANGELOG.md.
-      - name: Create Pull Request
-        uses: peter-evans/create-pull-request@v7
-        with:
-          token: ${{ secrets.GITHUB_TOKEN }}
-          sign-commits: true
-          commit-message: "chore: update CHANGELOG for release ${{ github.ref_name }}"
-          base: main
-          branch: "changelog/${{ github.ref_name }}"
-          reviewers: danny-avila
-          title: "📜 docs: Changelog for release ${{ github.ref_name }}"
-          body: |
-            **Description**:
-            - This PR updates the CHANGELOG.md by removing the "Unreleased" section and adding new release notes for release ${{ github.ref_name }} above previous releases.

.github/workflows/generate-unreleased-changelog-pr.yml

@@ -1,107 +0,0 @@
-name: Generate Unreleased Changelog PR
-
-on:
-  schedule:
-    - cron: "0 0 * * 1"  # Runs every Monday at 00:00 UTC
-  workflow_dispatch:
-
-jobs:
-  generate-unreleased-changelog-pr:
-    permissions:
-      contents: write    # Needed for pushing commits and creating branches.
-      pull-requests: write
-    runs-on: ubuntu-latest
-    steps:
-      # 1. Checkout the repository on main.
-      - name: Checkout Repository on Main
-        uses: actions/checkout@v4
-        with:
-          ref: main
-          fetch-depth: 0
-
-      # 4. Get the latest version tag.
-      - name: Get Latest Tag
-        id: get_latest_tag
-        run: |
-          LATEST_TAG=$(git describe --tags $(git rev-list --tags --max-count=1) || echo "none")
-          echo "Latest tag: $LATEST_TAG"
-          echo "tag=$LATEST_TAG" >> $GITHUB_OUTPUT
-
-      # 5. Generate the Unreleased changelog.
-      - name: Generate Unreleased Changelog
-        id: generate_unreleased
-        uses: mikepenz/release-changelog-builder-action@v5.1.0
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          configuration: ".github/configuration-unreleased.json"
-          owner: ${{ github.repository_owner }}
-          repo: ${{ github.event.repository.name }}
-          outputFile: CHANGELOG-unreleased.md
-          fromTag: ${{ steps.get_latest_tag.outputs.tag }}
-          toTag: main
-
-      # 7. Update CHANGELOG.md with the new Unreleased section.
-      - name: Update CHANGELOG.md
-        id: update_changelog
-        run: |
-          # Create CHANGELOG.md if it doesn't exist.
-          if [ ! -f CHANGELOG.md ]; then
-            echo "# Changelog" > CHANGELOG.md
-            echo "" >> CHANGELOG.md
-            echo "All notable changes to this project will be documented in this file." >> CHANGELOG.md
-            echo "" >> CHANGELOG.md
-          fi
-          
-          echo "Updating CHANGELOG.md…"
-          
-          # Extract content before the "## [Unreleased]" (or first version header if missing).
-          if grep -q "^## \[Unreleased\]" CHANGELOG.md; then
-            awk '/^## \[Unreleased\]/{exit} {print}' CHANGELOG.md > CHANGELOG_TMP.md
-          else
-            awk '/^## \[v/{exit} {print}' CHANGELOG.md > CHANGELOG_TMP.md
-          fi
-          
-          # Append the generated Unreleased changelog.
-          echo "" >> CHANGELOG_TMP.md
-          cat CHANGELOG-unreleased.md >> CHANGELOG_TMP.md
-          echo "" >> CHANGELOG_TMP.md
-          
-          # Append the remainder of the original changelog (starting from the first version header).
-          awk 'f{print} /^## \[v/{f=1; print}' CHANGELOG.md >> CHANGELOG_TMP.md
-          
-          # Replace the old file with the updated file.
-          mv CHANGELOG_TMP.md CHANGELOG.md
-          
-          # Remove the temporary generated file.
-          rm -f CHANGELOG-unreleased.md
-          
-          echo "Final CHANGELOG.md:"
-          cat CHANGELOG.md
-
-      # 8. Check if CHANGELOG.md has any updates.
-      - name: Check for CHANGELOG.md changes
-        id: changelog_changes
-        run: |
-          if git diff --quiet CHANGELOG.md; then
-            echo "has_changes=false" >> $GITHUB_OUTPUT
-          else
-            echo "has_changes=true" >> $GITHUB_OUTPUT
-          fi
-
-      # 9. Create (or update) the Pull Request only if there are changes.
-      - name: Create Pull Request
-        if: steps.changelog_changes.outputs.has_changes == 'true'
-        uses: peter-evans/create-pull-request@v7
-        with:
-          token: ${{ secrets.GITHUB_TOKEN }}
-          base: main
-          branch: "changelog/unreleased-update"
-          sign-commits: true
-          commit-message: "action: update Unreleased changelog"
-          title: "📜 docs: Unreleased Changelog"
-          body: |
-            **Description**:
-            - This PR updates the Unreleased section in CHANGELOG.md.
-            - It compares the current main branch with the latest version tag (determined as ${{ steps.get_latest_tag.outputs.tag }}),
-              regenerates the Unreleased changelog, removes any old Unreleased block, and inserts the new content.

.github/workflows/helmcharts.yml

@@ -4,12 +4,13 @@ name: Build Helm Charts on Tag
 on:
   push:
     tags:
-      - "*"
+      - "chart-*"
 
 jobs:
   release:
     permissions:
       contents: write
+      packages: write
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
@@ -26,15 +27,49 @@ jobs:
         uses: azure/setup-helm@v4
         env:
           GITHUB_TOKEN: "${{ secrets.GITHUB_TOKEN }}"
+      
       - name: Build Subchart Deps
         run: |
-          cd helm/librechat-rag-api
+          cd helm/librechat
+          helm dependency build  
+          cd ../librechat-rag-api
           helm dependency build      
 
-      - name: Run chart-releaser
-        uses: helm/chart-releaser-action@v1.6.0
+      - name: Get Chart Version
+        id: chart-version
+        run: |
+          CHART_VERSION=$(echo "${{ github.ref_name }}" | cut -d'-' -f2)
+          echo "CHART_VERSION=${CHART_VERSION}" >> "$GITHUB_OUTPUT"
+
+      # Log in to GitHub Container Registry
+      - name: Log in to GitHub Container Registry
+        uses: docker/login-action@v3
         with:
-          charts_dir: helm
-          skip_existing: true
-        env:
-          CR_TOKEN: "${{ secrets.GITHUB_TOKEN }}"
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      # Run Helm OCI Charts Releaser
+      # This is for the librechat chart
+      - name: Release Helm OCI Charts for librechat
+        uses: appany/helm-oci-chart-releaser@v0.4.2
+        with:
+          name: librechat
+          repository: ${{ github.actor }}/librechat-chart
+          tag: ${{ steps.chart-version.outputs.CHART_VERSION }}
+          path: helm/librechat
+          registry: ghcr.io
+          registry_username: ${{ github.actor }}
+          registry_password: ${{ secrets.GITHUB_TOKEN }}
+      
+      # this is for the librechat-rag-api chart
+      - name: Release Helm OCI Charts for librechat-rag-api
+        uses: appany/helm-oci-chart-releaser@v0.4.2
+        with:
+          name: librechat-rag-api
+          repository: ${{ github.actor }}/librechat-chart
+          tag: ${{ steps.chart-version.outputs.CHART_VERSION }}
+          path: helm/librechat-rag-api
+          registry: ghcr.io
+          registry_username: ${{ github.actor }}
+          registry_password: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/i18n-unused-keys.yml

@@ -1,11 +1,18 @@
 name: Detect Unused i18next Strings
 
+# This workflow checks for unused i18n keys in translation files.
+# It has special handling for:
+# - com_ui_special_var_* keys that are dynamically constructed
+# - com_agents_category_* keys that are stored in the database and used dynamically
+
 on:
   pull_request:
     paths:
       - "client/src/**"
       - "api/**"
       - "packages/data-provider/src/**"
+      - "packages/client/**"
+      - "packages/data-schemas/src/**"
 
 jobs:
   detect-unused-i18n-keys:
@@ -23,7 +30,7 @@ jobs:
 
           # Define paths
           I18N_FILE="client/src/locales/en/translation.json"
-          SOURCE_DIRS=("client/src" "api" "packages/data-provider/src")
+          SOURCE_DIRS=("client/src" "api" "packages/data-provider/src" "packages/client" "packages/data-schemas/src")
 
           # Check if translation file exists
           if [[ ! -f "$I18N_FILE" ]]; then
@@ -51,6 +58,31 @@ jobs:
                 fi
               done
               
+              # Also check if the key is directly used somewhere
+              if [[ "$FOUND" == false ]]; then
+                for DIR in "${SOURCE_DIRS[@]}"; do
+                  if grep -r --include=\*.{js,jsx,ts,tsx} -q "$KEY" "$DIR"; then
+                    FOUND=true
+                    break
+                  fi
+                done
+              fi
+            # Special case for agent category keys that are dynamically used from database
+            elif [[ "$KEY" == com_agents_category_* ]]; then
+              # Check if agent category localization is being used
+              for DIR in "${SOURCE_DIRS[@]}"; do
+                # Check for dynamic category label/description usage
+                if grep -r --include=\*.{js,jsx,ts,tsx} -E "category\.(label|description).*startsWith.*['\"]com_" "$DIR" > /dev/null 2>&1 || \
+                   # Check for the method that defines these keys
+                   grep -r --include=\*.{js,jsx,ts,tsx} "ensureDefaultCategories" "$DIR" > /dev/null 2>&1 || \
+                   # Check for direct usage in agentCategory.ts
+                   grep -r --include=\*.ts -E "label:.*['\"]$KEY['\"]" "$DIR" > /dev/null 2>&1 || \
+                   grep -r --include=\*.ts -E "description:.*['\"]$KEY['\"]" "$DIR" > /dev/null 2>&1; then
+                  FOUND=true
+                  break
+                fi
+              done
+              
               # Also check if the key is directly used somewhere
               if [[ "$FOUND" == false ]]; then
                 for DIR in "${SOURCE_DIRS[@]}"; do

.github/workflows/locize-i18n-sync.yml

@@ -48,7 +48,7 @@ jobs:
 
       # 2. Download translation files from locize.
       - name: Download Translations from locize
-        uses: locize/download@v1
+        uses: locize/download@v2
         with:
           project-id: ${{ secrets.LOCIZE_PROJECT_ID }}
           path: "client/src/locales"

.github/workflows/unused-packages.yml

@@ -7,6 +7,7 @@ on:
       - 'package-lock.json'
       - 'client/**'
       - 'api/**'
+      - 'packages/client/**'
 
 jobs:
   detect-unused-packages:
@@ -28,7 +29,7 @@ jobs:
 
       - name: Validate JSON files
         run: |
-          for FILE in package.json client/package.json api/package.json; do
+          for FILE in package.json client/package.json api/package.json packages/client/package.json; do
             if [[ -f "$FILE" ]]; then
               jq empty "$FILE" || (echo "::error title=Invalid JSON::$FILE is invalid" && exit 1)
             fi
@@ -63,12 +64,31 @@ jobs:
             local folder=$1
             local output_file=$2
             if [[ -d "$folder" ]]; then
-              grep -rEho "require\\(['\"]([a-zA-Z0-9@/._-]+)['\"]\\)" "$folder" --include=\*.{js,ts,mjs,cjs} | \
+              # Extract require() statements
+              grep -rEho "require\\(['\"]([a-zA-Z0-9@/._-]+)['\"]\\)" "$folder" --include=\*.{js,ts,tsx,jsx,mjs,cjs} | \
                 sed -E "s/require\\(['\"]([a-zA-Z0-9@/._-]+)['\"]\\)/\1/" > "$output_file"
           
-              grep -rEho "import .* from ['\"]([a-zA-Z0-9@/._-]+)['\"]" "$folder" --include=\*.{js,ts,mjs,cjs} | \
+              # Extract ES6 imports - various patterns
+              # import x from 'module'
+              grep -rEho "import .* from ['\"]([a-zA-Z0-9@/._-]+)['\"]" "$folder" --include=\*.{js,ts,tsx,jsx,mjs,cjs} | \
                 sed -E "s/import .* from ['\"]([a-zA-Z0-9@/._-]+)['\"]/\1/" >> "$output_file"
               
+              # import 'module' (side-effect imports)
+              grep -rEho "import ['\"]([a-zA-Z0-9@/._-]+)['\"]" "$folder" --include=\*.{js,ts,tsx,jsx,mjs,cjs} | \
+                sed -E "s/import ['\"]([a-zA-Z0-9@/._-]+)['\"]/\1/" >> "$output_file"
+              
+              # export { x } from 'module' or export * from 'module'
+              grep -rEho "export .* from ['\"]([a-zA-Z0-9@/._-]+)['\"]" "$folder" --include=\*.{js,ts,tsx,jsx,mjs,cjs} | \
+                sed -E "s/export .* from ['\"]([a-zA-Z0-9@/._-]+)['\"]/\1/" >> "$output_file"
+              
+              # import type { x } from 'module' (TypeScript)
+              grep -rEho "import type .* from ['\"]([a-zA-Z0-9@/._-]+)['\"]" "$folder" --include=\*.{ts,tsx} | \
+                sed -E "s/import type .* from ['\"]([a-zA-Z0-9@/._-]+)['\"]/\1/" >> "$output_file"
+          
+              # Remove subpath imports but keep the base package
+              # e.g., '@tanstack/react-query/devtools' becomes '@tanstack/react-query'
+              sed -i -E 's|^(@?[a-zA-Z0-9-]+(/[a-zA-Z0-9-]+)?)/.*|\1|' "$output_file"
+              
               sort -u "$output_file" -o "$output_file"
             else
               touch "$output_file"
@@ -79,12 +99,79 @@ jobs:
           extract_deps_from_code "client" client_used_code.txt
           extract_deps_from_code "api" api_used_code.txt
           
+          # Extract dependencies used by @librechat/client package
+          extract_deps_from_code "packages/client" packages_client_used_code.txt
+
+      - name: Get @librechat/client dependencies
+        id: get-librechat-client-deps
+        run: |
+          if [[ -f "packages/client/package.json" ]]; then
+            # Get all dependencies from @librechat/client (dependencies, devDependencies, and peerDependencies)
+            DEPS=$(jq -r '.dependencies // {} | keys[]' packages/client/package.json 2>/dev/null || echo "")
+            DEV_DEPS=$(jq -r '.devDependencies // {} | keys[]' packages/client/package.json 2>/dev/null || echo "")
+            PEER_DEPS=$(jq -r '.peerDependencies // {} | keys[]' packages/client/package.json 2>/dev/null || echo "")
+            
+            # Combine all dependencies
+            echo "$DEPS" > librechat_client_deps.txt
+            echo "$DEV_DEPS" >> librechat_client_deps.txt
+            echo "$PEER_DEPS" >> librechat_client_deps.txt
+            
+            # Also include dependencies that are imported in packages/client
+            cat packages_client_used_code.txt >> librechat_client_deps.txt
+            
+            # Remove empty lines and sort
+            grep -v '^$' librechat_client_deps.txt | sort -u > temp_deps.txt
+            mv temp_deps.txt librechat_client_deps.txt
+          else
+            touch librechat_client_deps.txt
+          fi
+
+      - name: Extract Workspace Dependencies
+        id: extract-workspace-deps
+        run: |
+          # Function to get dependencies from a workspace package that are used by another package
+          get_workspace_package_deps() {
+            local package_json=$1
+            local output_file=$2
+            
+            # Get all workspace dependencies (starting with @librechat/)
+            if [[ -f "$package_json" ]]; then
+              local workspace_deps=$(jq -r '.dependencies // {} | to_entries[] | select(.key | startswith("@librechat/")) | .key' "$package_json" 2>/dev/null || echo "")
+              
+              # For each workspace dependency, get its dependencies
+              for dep in $workspace_deps; do
+                # Convert @librechat/api to packages/api
+                local workspace_path=$(echo "$dep" | sed 's/@librechat\//packages\//')
+                local workspace_package_json="${workspace_path}/package.json"
+                
+                if [[ -f "$workspace_package_json" ]]; then
+                  # Extract all dependencies from the workspace package
+                  jq -r '.dependencies // {} | keys[]' "$workspace_package_json" 2>/dev/null >> "$output_file"
+                  # Also extract peerDependencies
+                  jq -r '.peerDependencies // {} | keys[]' "$workspace_package_json" 2>/dev/null >> "$output_file"
+                fi
+              done
+            fi
+            
+            if [[ -f "$output_file" ]]; then
+              sort -u "$output_file" -o "$output_file"
+            else
+              touch "$output_file"
+            fi
+          }
+          
+          # Get workspace dependencies for each package
+          get_workspace_package_deps "package.json" root_workspace_deps.txt
+          get_workspace_package_deps "client/package.json" client_workspace_deps.txt
+          get_workspace_package_deps "api/package.json" api_workspace_deps.txt
+
       - name: Run depcheck for root package.json
         id: check-root
         run: |
           if [[ -f "package.json" ]]; then
             UNUSED=$(depcheck --json | jq -r '.dependencies | join("\n")' || echo "")
-            UNUSED=$(comm -23 <(echo "$UNUSED" | sort) <(cat root_used_deps.txt root_used_code.txt | sort) || echo "")
+            # Exclude dependencies used in scripts, code, and workspace packages
+            UNUSED=$(comm -23 <(echo "$UNUSED" | sort) <(cat root_used_deps.txt root_used_code.txt root_workspace_deps.txt | sort) || echo "")
             echo "ROOT_UNUSED<<EOF" >> $GITHUB_ENV
             echo "$UNUSED" >> $GITHUB_ENV
             echo "EOF" >> $GITHUB_ENV
@@ -97,7 +184,8 @@ jobs:
             chmod -R 755 client
             cd client
             UNUSED=$(depcheck --json | jq -r '.dependencies | join("\n")' || echo "")
-            UNUSED=$(comm -23 <(echo "$UNUSED" | sort) <(cat ../client_used_deps.txt ../client_used_code.txt | sort) || echo "")
+            # Exclude dependencies used in scripts, code, and workspace packages
+            UNUSED=$(comm -23 <(echo "$UNUSED" | sort) <(cat ../client_used_deps.txt ../client_used_code.txt ../client_workspace_deps.txt | sort) || echo "")
             # Filter out false positives
             UNUSED=$(echo "$UNUSED" | grep -v "^micromark-extension-llm-math$" || echo "")
             echo "CLIENT_UNUSED<<EOF" >> $GITHUB_ENV
@@ -113,7 +201,8 @@ jobs:
             chmod -R 755 api
             cd api
             UNUSED=$(depcheck --json | jq -r '.dependencies | join("\n")' || echo "")
-            UNUSED=$(comm -23 <(echo "$UNUSED" | sort) <(cat ../api_used_deps.txt ../api_used_code.txt | sort) || echo "")
+            # Exclude dependencies used in scripts, code, and workspace packages
+            UNUSED=$(comm -23 <(echo "$UNUSED" | sort) <(cat ../api_used_deps.txt ../api_used_code.txt ../api_workspace_deps.txt | sort) || echo "")
             echo "API_UNUSED<<EOF" >> $GITHUB_ENV
             echo "$UNUSED" >> $GITHUB_ENV
             echo "EOF" >> $GITHUB_ENV

.gitignore

@@ -13,6 +13,9 @@ pids
 *.seed
 .git
 
+# CI/CD data
+test-image*
+
 # Directory for instrumented libs generated by jscoverage/JSCover
 lib-cov
 
@@ -125,3 +128,13 @@ helm/**/.values.yaml
 
 # SAML Idp cert
 *.cert
+
+# AI Assistants
+/.claude/
+/.cursor/
+/.copilot/
+/.aider/
+/.openai/
+/.tabnine/
+/.codeium
+*.local.md

.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

.vscode/launch.json

@@ -8,7 +8,8 @@
       "skipFiles": ["<node_internals>/**"],
       "program": "${workspaceFolder}/api/server/index.js",
       "env": {
-        "NODE_ENV": "production"
+        "NODE_ENV": "production",
+        "NODE_TLS_REJECT_UNAUTHORIZED": "0"
       },
       "console": "integratedTerminal",
       "envFile": "${workspaceFolder}/.env"

Dockerfile

@@ -1,4 +1,4 @@
-# v0.7.8
+# v0.8.1-rc1
 
 # Base node image
 FROM node:20-alpine AS node
@@ -19,24 +19,31 @@ WORKDIR /app
 
 USER node
 
-COPY --chown=node:node . .
+COPY --chown=node:node package.json package-lock.json ./
+COPY --chown=node:node api/package.json ./api/package.json
+COPY --chown=node:node client/package.json ./client/package.json
+COPY --chown=node:node packages/data-provider/package.json ./packages/data-provider/package.json
+COPY --chown=node:node packages/data-schemas/package.json ./packages/data-schemas/package.json
+COPY --chown=node:node packages/api/package.json ./packages/api/package.json
 
 RUN \
     # Allow mounting of these files, which have no default
     touch .env ; \
     # Create directories for the volumes to inherit the correct permissions
-    mkdir -p /app/client/public/images /app/api/logs ; \
+    mkdir -p /app/client/public/images /app/api/logs /app/uploads ; \
     npm config set fetch-retry-maxtimeout 600000 ; \
     npm config set fetch-retries 5 ; \
     npm config set fetch-retry-mintimeout 15000 ; \
-    npm install --no-audit; \
+    npm ci --no-audit
+
+COPY --chown=node:node . .
+
+RUN \
     # React client build
     NODE_OPTIONS="--max-old-space-size=2048" npm run frontend; \
     npm prune --production; \
     npm cache clean --force
 
-RUN mkdir -p /app/client/public/images /app/api/logs
-
 # Node API setup
 EXPOSE 3080
 ENV HOST=0.0.0.0

Dockerfile.multi

@@ -1,5 +1,5 @@
 # Dockerfile.multi
-# v0.7.8
+# v0.8.1-rc1
 
 # Base for all builds
 FROM node:20-alpine AS base-min
@@ -16,6 +16,7 @@ COPY package*.json ./
 COPY packages/data-provider/package*.json ./packages/data-provider/
 COPY packages/api/package*.json ./packages/api/
 COPY packages/data-schemas/package*.json ./packages/data-schemas/
+COPY packages/client/package*.json ./packages/client/
 COPY client/package*.json ./client/
 COPY api/package*.json ./api/
 
@@ -45,11 +46,19 @@ COPY --from=data-provider-build /app/packages/data-provider/dist /app/packages/d
 COPY --from=data-schemas-build /app/packages/data-schemas/dist /app/packages/data-schemas/dist
 RUN npm run build
 
+# Build `client` package
+FROM base AS client-package-build
+WORKDIR /app/packages/client
+COPY packages/client ./
+RUN npm run build
+
 # Client build
 FROM base AS client-build
 WORKDIR /app/client
 COPY client ./
 COPY --from=data-provider-build /app/packages/data-provider/dist /app/packages/data-provider/dist
+COPY --from=client-package-build /app/packages/client/dist /app/packages/client/dist
+COPY --from=client-package-build /app/packages/client/src /app/packages/client/src
 ENV NODE_OPTIONS="--max-old-space-size=2048"
 RUN npm run build
 

README.md

@@ -52,7 +52,7 @@
 - 🖥️ **UI & Experience** inspired by ChatGPT with enhanced design and features
 
 - 🤖 **AI Model Selection**:  
-  - Anthropic (Claude), AWS Bedrock, OpenAI, Azure OpenAI, Google, Vertex AI, OpenAI Assistants API (incl. Azure)
+  - Anthropic (Claude), AWS Bedrock, OpenAI, Azure OpenAI, Google, Vertex AI, OpenAI Responses API (incl. Azure)
   - [Custom Endpoints](https://www.librechat.ai/docs/quick_start/custom_endpoints): Use any OpenAI-compatible API with LibreChat, no proxy required
   - Compatible with [Local & Remote AI Providers](https://www.librechat.ai/docs/configuration/librechat_yaml/ai_endpoints):
     - Ollama, groq, Cohere, Mistral AI, Apple MLX, koboldcpp, together.ai,
@@ -65,15 +65,17 @@
 
 - 🔦 **Agents & Tools Integration**:  
   - **[LibreChat Agents](https://www.librechat.ai/docs/features/agents)**:
-    - No-Code Custom Assistants: Build specialized, AI-driven helpers without coding  
-    - Flexible & Extensible: Attach tools like DALL-E-3, file search, code execution, and more  
-    - Compatible with Custom Endpoints, OpenAI, Azure, Anthropic, AWS Bedrock, and more
+    - No-Code Custom Assistants: Build specialized, AI-driven helpers
+    - Agent Marketplace: Discover and deploy community-built agents
+    - Collaborative Sharing: Share agents with specific users and groups
+    - Flexible & Extensible: Use MCP Servers, tools, file search, code execution, and more
+    - Compatible with Custom Endpoints, OpenAI, Azure, Anthropic, AWS Bedrock, Google, Vertex AI, Responses API, and more
     - [Model Context Protocol (MCP) Support](https://modelcontextprotocol.io/clients#librechat) for Tools
-  - Use LibreChat Agents and OpenAI Assistants with Files, Code Interpreter, Tools, and API Actions
 
 - 🔍 **Web Search**:  
   - Search the internet and retrieve relevant information to enhance your AI context
   - Combines search providers, content scrapers, and result rerankers for optimal results
+  - **Customizable Jina Reranking**: Configure custom Jina API URLs for reranking services
   - **[Learn More →](https://www.librechat.ai/docs/features/web_search)**
 
 - 🪄 **Generative UI with Code Artifacts**:  
@@ -88,6 +90,7 @@
   - Create, Save, & Share Custom Presets  
   - Switch between AI Endpoints and Presets mid-chat
   - Edit, Resubmit, and Continue Messages with Conversation branching  
+  - Create and share prompts with specific users and groups
   - [Fork Messages & Conversations](https://www.librechat.ai/docs/features/fork) for Advanced Context control
 
 - 💬 **Multimodal & File Interactions**:  
@@ -95,8 +98,10 @@
   - Chat with Files using Custom Endpoints, OpenAI, Azure, Anthropic, AWS Bedrock, & Google 🗃️
 
 - 🌎 **Multilingual UI**:
-  - English, 中文, Deutsch, Español, Français, Italiano, Polski, Português Brasileiro
-  - Русский, 日本語, Svenska, 한국어, Tiếng Việt, 繁體中文, العربية, Türkçe, Nederlands, עברית
+  - English, 中文 (简体), 中文 (繁體), العربية, Deutsch, Español, Français, Italiano
+  - Polski, Português (PT), Português (BR), Русский, 日本語, Svenska, 한국어, Tiếng Việt
+  - Türkçe, Nederlands, עברית, Català, Čeština, Dansk, Eesti, فارسی
+  - Suomi, Magyar, Հայերեն, Bahasa Indonesia, ქართული, Latviešu, ไทย, ئۇيغۇرچە
 
 - 🧠 **Reasoning UI**:  
   - Dynamic Reasoning UI for Chain-of-Thought/Reasoning AI models like DeepSeek-R1

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,
@@ -9,8 +10,18 @@ const {
   getResponseSender,
   validateVisionModel,
 } = require('librechat-data-provider');
-const { SplitStreamHandler: _Handler } = require('@librechat/agents');
-const { Tokenizer, createFetch, createStreamEventHandlers } = require('@librechat/api');
+const { sleep, SplitStreamHandler: _Handler } = require('@librechat/agents');
+const {
+  Tokenizer,
+  createFetch,
+  matchModelName,
+  getClaudeHeaders,
+  getModelMaxTokens,
+  configureReasoning,
+  checkPromptCacheSupport,
+  getModelMaxOutputTokens,
+  createStreamEventHandlers,
+} = require('@librechat/api');
 const {
   truncateText,
   formatMessage,
@@ -19,17 +30,9 @@ const {
   parseParamFromPrompt,
   createContextHandlers,
 } = require('./prompts');
-const {
-  getClaudeHeaders,
-  configureReasoning,
-  checkPromptCacheSupport,
-} = require('~/server/services/Endpoints/anthropic/helpers');
-const { getModelMaxTokens, getModelMaxOutputTokens, matchModelName } = require('~/utils');
 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

@@ -1,22 +1,31 @@
 const crypto = require('crypto');
 const fetch = require('node-fetch');
+const { logger } = require('@librechat/data-schemas');
 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 { addSpaceIfNeeded } = require('~/server/utils');
+const countTokens = require('~/server/utils/countTokens');
 const { getFiles } = require('~/models/File');
 const TextStream = require('./TextStream');
-const { logger } = require('~/config');
 
 class BaseClient {
   constructor(apiKey, options = {}) {
@@ -38,6 +47,8 @@ class BaseClient {
     this.conversationId;
     /** @type {string} */
     this.responseMessageId;
+    /** @type {string} */
+    this.parentMessageId;
     /** @type {TAttachment[]} */
     this.attachments;
     /** The key for the usage object's input tokens
@@ -109,12 +120,17 @@ class BaseClient {
   /**
    * Abstract method to record token usage. Subclasses must implement this method.
    * If a correction to the token usage is needed, the method should return an object with the corrected token counts.
+   * Should only be used if `recordCollectedUsage` was not used instead.
+   * @param {string} [model]
+   * @param {AppConfig['balance']} [balance]
    * @param {number} promptTokens
    * @param {number} completionTokens
    * @returns {Promise<void>}
    */
-  async recordTokenUsage({ promptTokens, completionTokens }) {
+  async recordTokenUsage({ model, balance, promptTokens, completionTokens }) {
     logger.debug('[BaseClient] `recordTokenUsage` not implemented.', {
+      model,
+      balance,
       promptTokens,
       completionTokens,
     });
@@ -183,7 +199,8 @@ class BaseClient {
     this.user = user;
     const saveOptions = this.getSaveOptions();
     this.abortController = opts.abortController ?? new AbortController();
-    const conversationId = overrideConvoId ?? opts.conversationId ?? crypto.randomUUID();
+    const requestConvoId = overrideConvoId ?? opts.conversationId;
+    const conversationId = requestConvoId ?? crypto.randomUUID();
     const parentMessageId = opts.parentMessageId ?? Constants.NO_PARENT;
     const userMessageId =
       overrideUserMessageId ?? opts.overrideParentMessageId ?? crypto.randomUUID();
@@ -198,17 +215,22 @@ class BaseClient {
       this.currentMessages[this.currentMessages.length - 1].messageId = head;
     }
 
+    if (opts.isRegenerate && responseMessageId.endsWith('_')) {
+      responseMessageId = crypto.randomUUID();
+    }
+
     this.responseMessageId = responseMessageId;
 
     return {
       ...opts,
       user,
       head,
+      saveOptions,
+      userMessageId,
+      requestConvoId,
       conversationId,
       parentMessageId,
-      userMessageId,
       responseMessageId,
-      saveOptions,
     };
   }
 
@@ -227,11 +249,12 @@ class BaseClient {
     const {
       user,
       head,
+      saveOptions,
+      userMessageId,
+      requestConvoId,
       conversationId,
       parentMessageId,
-      userMessageId,
       responseMessageId,
-      saveOptions,
     } = await this.setMessageOptions(opts);
 
     const userMessage = opts.isEdited
@@ -253,7 +276,8 @@ class BaseClient {
     }
 
     if (typeof opts?.onStart === 'function') {
-      opts.onStart(userMessage, responseMessageId);
+      const isNewConvo = !requestConvoId && parentMessageId === Constants.NO_PARENT;
+      opts.onStart(userMessage, responseMessageId, isNewConvo);
     }
 
     return {
@@ -559,6 +583,7 @@ class BaseClient {
   }
 
   async sendMessage(message, opts = {}) {
+    const appConfig = this.options.req?.config;
     /** @type {Promise<TMessage>} */
     let userMessagePromise;
     const { user, head, isEdited, conversationId, responseMessageId, saveOptions, userMessage } =
@@ -572,7 +597,7 @@ class BaseClient {
       });
     }
 
-    const { generation = '' } = opts;
+    const { editedContent } = opts;
 
     // It's not necessary to push to currentMessages
     // depending on subclass implementation of handling messages
@@ -587,26 +612,40 @@ class BaseClient {
           isCreatedByUser: false,
           model: this.modelOptions?.model ?? this.model,
           sender: this.sender,
-          text: generation,
         };
         this.currentMessages.push(userMessage, latestMessage);
-      } else {
-        latestMessage.text = generation;
+      } else if (editedContent != null) {
+        // Handle editedContent for content parts
+        if (editedContent && latestMessage.content && Array.isArray(latestMessage.content)) {
+          const { index, text, type } = editedContent;
+          if (index >= 0 && index < latestMessage.content.length) {
+            const contentPart = latestMessage.content[index];
+            if (type === ContentTypes.THINK && contentPart.type === ContentTypes.THINK) {
+              contentPart[ContentTypes.THINK] = text;
+            } else if (type === ContentTypes.TEXT && contentPart.type === ContentTypes.TEXT) {
+              contentPart[ContentTypes.TEXT] = text;
+            }
+          }
+        }
       }
       this.continued = true;
     } else {
       this.currentMessages.push(userMessage);
     }
 
+    /**
+     * When the userMessage is pushed to currentMessages, the parentMessage is the userMessageId.
+     * this only matters when buildMessages is utilizing the parentMessageId, and may vary on implementation
+     */
+    const parentMessageId = isEdited ? head : userMessage.messageId;
+    this.parentMessageId = parentMessageId;
     let {
       prompt: payload,
       tokenCountMap,
       promptTokens,
     } = await this.buildMessages(
       this.currentMessages,
-      // When the userMessage is pushed to currentMessages, the parentMessage is the userMessageId.
-      // this only matters when buildMessages is utilizing the parentMessageId, and may vary on implementation
-      isEdited ? head : userMessage.messageId,
+      parentMessageId,
       this.getBuildMessagesOptions(opts),
       opts,
     );
@@ -631,9 +670,9 @@ class BaseClient {
       }
     }
 
-    const balance = this.options.req?.app?.locals?.balance;
+    const balanceConfig = getBalanceConfig(appConfig);
     if (
-      balance?.enabled &&
+      balanceConfig?.enabled &&
       supportsBalanceCheck[this.options.endpointType ?? this.options.endpoint]
     ) {
       await checkBalance({
@@ -672,16 +711,32 @@ class BaseClient {
     };
 
     if (typeof completion === 'string') {
-      responseMessage.text = addSpaceIfNeeded(generation) + completion;
+      responseMessage.text = completion;
     } else if (
       Array.isArray(completion) &&
       (this.clientName === EModelEndpoint.agents ||
         isParamEndpoint(this.options.endpoint, this.options.endpointType))
     ) {
       responseMessage.text = '';
-      responseMessage.content = completion;
+
+      if (!opts.editedContent || this.currentMessages.length === 0) {
+        responseMessage.content = completion;
+      } else {
+        const latestMessage = this.currentMessages[this.currentMessages.length - 1];
+        if (!latestMessage?.content) {
+          responseMessage.content = completion;
+        } else {
+          const existingContent = [...latestMessage.content];
+          const { type: editedType } = opts.editedContent;
+          responseMessage.content = this.mergeEditedContent(
+            existingContent,
+            completion,
+            editedType,
+          );
+        }
+      }
     } else if (Array.isArray(completion)) {
-      responseMessage.text = addSpaceIfNeeded(generation) + completion.join('');
+      responseMessage.text = completion.join('');
     }
 
     if (
@@ -712,9 +767,14 @@ class BaseClient {
       } else {
         responseMessage.tokenCount = this.getTokenCountForResponse(responseMessage);
         completionTokens = responseMessage.tokenCount;
+        await this.recordTokenUsage({
+          usage,
+          promptTokens,
+          completionTokens,
+          balance: balanceConfig,
+          model: responseMessage.model,
+        });
       }
-
-      await this.recordTokenUsage({ promptTokens, completionTokens, usage });
     }
 
     if (userMessagePromise) {
@@ -1095,6 +1155,50 @@ class BaseClient {
     return numTokens;
   }
 
+  /**
+   * Merges completion content with existing content when editing TEXT or THINK types
+   * @param {Array} existingContent - The existing content array
+   * @param {Array} newCompletion - The new completion content
+   * @param {string} editedType - The type of content being edited
+   * @returns {Array} The merged content array
+   */
+  mergeEditedContent(existingContent, newCompletion, editedType) {
+    if (!newCompletion.length) {
+      return existingContent.concat(newCompletion);
+    }
+
+    if (editedType !== ContentTypes.TEXT && editedType !== ContentTypes.THINK) {
+      return existingContent.concat(newCompletion);
+    }
+
+    const lastIndex = existingContent.length - 1;
+    const lastExisting = existingContent[lastIndex];
+    const firstNew = newCompletion[0];
+
+    if (lastExisting?.type !== firstNew?.type || firstNew?.type !== editedType) {
+      return existingContent.concat(newCompletion);
+    }
+
+    const mergedContent = [...existingContent];
+    if (editedType === ContentTypes.TEXT) {
+      mergedContent[lastIndex] = {
+        ...mergedContent[lastIndex],
+        [ContentTypes.TEXT]:
+          (mergedContent[lastIndex][ContentTypes.TEXT] || '') + (firstNew[ContentTypes.TEXT] || ''),
+      };
+    } else {
+      mergedContent[lastIndex] = {
+        ...mergedContent[lastIndex],
+        [ContentTypes.THINK]:
+          (mergedContent[lastIndex][ContentTypes.THINK] || '') +
+          (firstNew[ContentTypes.THINK] || ''),
+      };
+    }
+
+    // Add remaining completion items
+    return mergedContent.concat(newCompletion.slice(1));
+  }
+
   async sendPayload(payload, opts = {}) {
     if (opts && typeof opts === 'object') {
       this.setOptions(opts);
@@ -1103,8 +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[]>}
    */
@@ -1153,7 +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 +1,7 @@
 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');
 const { Tokenizer, getSafetySettings } = require('@librechat/api');
@@ -21,9 +24,6 @@ const {
 } = require('librechat-data-provider');
 const { encodeAndFormat } = require('~/server/services/Files/images');
 const { spendTokens } = require('~/models/spendTokens');
-const { getModelMaxTokens } = require('~/utils');
-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

@@ -1,13 +1,15 @@
-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,
   createFetch,
   resolveHeaders,
   constructAzureURL,
+  getModelMaxTokens,
   genAzureChatCompletion,
+  getModelMaxOutputTokens,
   createStreamEventHandlers,
 } = require('@librechat/api');
 const {
@@ -31,17 +33,16 @@ const {
   titleInstruction,
   createContextHandlers,
 } = require('./prompts');
-const { extractBaseURL, getModelMaxTokens, getModelMaxOutputTokens } = require('~/utils');
 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 { createLLM, RunManager } = require('./llm');
+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 { logger } = require('~/config');
 
 class OpenAIClient extends BaseClient {
   constructor(apiKey, options = {}) {
@@ -612,77 +613,8 @@ class OpenAIClient extends BaseClient {
     return (reply ?? '').trim();
   }
 
-  initializeLLM({
-    model = openAISettings.model.default,
-    modelName,
-    temperature = 0.2,
-    max_tokens,
-    streaming,
-    context,
-    tokenBuffer,
-    initialMessageCount,
-    conversationId,
-  }) {
-    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,
-          ...configOptions?.baseOptions?.headers,
-        }),
-      };
-    }
-
-    if (this.options.proxy) {
-      configOptions.httpAgent = new HttpsProxyAgent(this.options.proxy);
-      configOptions.httpsAgent = new HttpsProxyAgent(this.options.proxy);
-    }
-
-    const { req, res, debug } = this.options;
-    const runManager = new RunManager({ req, res, debug, abortController: this.abortController });
-    this.runManager = runManager;
-
-    const llm = createLLM({
-      modelOptions,
-      configOptions,
-      openAIApiKey: this.apiKey,
-      azure: this.azure,
-      streaming,
-      callbacks: runManager.createCallbacks({
-        context,
-        tokenBuffer,
-        conversationId: this.conversationId ?? conversationId,
-        initialMessageCount,
-      }),
-    });
-
-    return llm;
+  initializeLLM() {
+    throw new Error('Deprecated');
   }
 
   /**
@@ -700,6 +632,7 @@ class OpenAIClient extends BaseClient {
    *                            In case of failure, it will return the default title, "New Chat".
    */
   async titleConvo({ text, conversationId, responseText = '' }) {
+    const appConfig = this.options.req?.config;
     this.conversationId = conversationId;
 
     if (this.options.attachments) {
@@ -728,8 +661,7 @@ class OpenAIClient extends BaseClient {
       max_tokens: 16,
     };
 
-    /** @type {TAzureConfig | undefined} */
-    const azureConfig = this.options?.req?.app?.locals?.[EModelEndpoint.azureOpenAI];
+    const azureConfig = appConfig?.endpoints?.[EModelEndpoint.azureOpenAI];
 
     const resetTitleOptions = !!(
       (this.azure && azureConfig) ||
@@ -749,7 +681,7 @@ class OpenAIClient extends BaseClient {
         groupMap,
       });
 
-      this.options.headers = resolveHeaders(headers);
+      this.options.headers = resolveHeaders({ headers });
       this.options.reverseProxyUrl = baseURL ?? null;
       this.langchainProxy = extractBaseURL(this.options.reverseProxyUrl);
       this.apiKey = azureOptions.azureOpenAIApiKey;
@@ -1118,6 +1050,7 @@ ${convo}
   }
 
   async chatCompletion({ payload, onProgress, abortController = null }) {
+    const appConfig = this.options.req?.config;
     let error = null;
     let intermediateReply = [];
     const errorCallback = (err) => (error = err);
@@ -1163,8 +1096,7 @@ ${convo}
         opts.fetchOptions.agent = new HttpsProxyAgent(this.options.proxy);
       }
 
-      /** @type {TAzureConfig | undefined} */
-      const azureConfig = this.options?.req?.app?.locals?.[EModelEndpoint.azureOpenAI];
+      const azureConfig = appConfig?.endpoints?.[EModelEndpoint.azureOpenAI];
 
       if (
         (this.azure && this.isVisionModel && azureConfig) ||
@@ -1181,7 +1113,7 @@ ${convo}
           modelGroupMap,
           groupMap,
         });
-        opts.defaultHeaders = resolveHeaders(headers);
+        opts.defaultHeaders = resolveHeaders({ headers });
         this.langchainProxy = extractBaseURL(baseURL);
         this.apiKey = azureOptions.azureOpenAIApiKey;
 
@@ -1222,7 +1154,9 @@ ${convo}
       }
 
       if (this.isOmni === true && modelOptions.max_tokens != null) {
-        modelOptions.max_completion_tokens = modelOptions.max_tokens;
+        const paramName =
+          modelOptions.useResponsesApi === true ? 'max_output_tokens' : 'max_completion_tokens';
+        modelOptions[paramName] = modelOptions.max_tokens;
         delete modelOptions.max_tokens;
       }
       if (this.isOmni === true && modelOptions.temperature != null) {

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/callbacks/createStartHandler.js

@@ -1,95 +0,0 @@
-const { promptTokensEstimate } = require('openai-chat-tokens');
-const { EModelEndpoint, supportsBalanceCheck } = require('librechat-data-provider');
-const { formatFromLangChain } = require('~/app/clients/prompts');
-const { getBalanceConfig } = require('~/server/services/Config');
-const { checkBalance } = require('~/models/balanceMethods');
-const { logger } = require('~/config');
-
-const createStartHandler = ({
-  context,
-  conversationId,
-  tokenBuffer = 0,
-  initialMessageCount,
-  manager,
-}) => {
-  return async (_llm, _messages, runId, parentRunId, extraParams) => {
-    const { invocation_params } = extraParams;
-    const { model, functions, function_call } = invocation_params;
-    const messages = _messages[0].map(formatFromLangChain);
-
-    logger.debug(`[createStartHandler] handleChatModelStart: ${context}`, {
-      model,
-      function_call,
-    });
-
-    if (context !== 'title') {
-      logger.debug(`[createStartHandler] handleChatModelStart: ${context}`, {
-        functions,
-      });
-    }
-
-    const payload = { messages };
-    let prelimPromptTokens = 1;
-
-    if (functions) {
-      payload.functions = functions;
-      prelimPromptTokens += 2;
-    }
-
-    if (function_call) {
-      payload.function_call = function_call;
-      prelimPromptTokens -= 5;
-    }
-
-    prelimPromptTokens += promptTokensEstimate(payload);
-    logger.debug('[createStartHandler]', {
-      prelimPromptTokens,
-      tokenBuffer,
-    });
-    prelimPromptTokens += tokenBuffer;
-
-    try {
-      const balance = await getBalanceConfig();
-      if (balance?.enabled && supportsBalanceCheck[EModelEndpoint.openAI]) {
-        const generations =
-          initialMessageCount && messages.length > initialMessageCount
-            ? messages.slice(initialMessageCount)
-            : null;
-        await checkBalance({
-          req: manager.req,
-          res: manager.res,
-          txData: {
-            user: manager.user,
-            tokenType: 'prompt',
-            amount: prelimPromptTokens,
-            debug: manager.debug,
-            generations,
-            model,
-            endpoint: EModelEndpoint.openAI,
-          },
-        });
-      }
-    } catch (err) {
-      logger.error(`[createStartHandler][${context}] checkBalance error`, err);
-      manager.abortController.abort();
-      if (context === 'summary' || context === 'plugins') {
-        manager.addRun(runId, { conversationId, error: err.message });
-        throw new Error(err);
-      }
-      return;
-    }
-
-    manager.addRun(runId, {
-      model,
-      messages,
-      functions,
-      function_call,
-      runId,
-      parentRunId,
-      conversationId,
-      prelimPromptTokens,
-    });
-  };
-};
-
-module.exports = createStartHandler;

api/app/clients/callbacks/index.js

@@ -1,5 +0,0 @@
-const createStartHandler = require('./createStartHandler');
-
-module.exports = {
-  createStartHandler,
-};

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/RunManager.js

@@ -1,105 +0,0 @@
-const { createStartHandler } = require('~/app/clients/callbacks');
-const { spendTokens } = require('~/models/spendTokens');
-const { logger } = require('~/config');
-
-class RunManager {
-  constructor(fields) {
-    const { req, res, abortController, debug } = fields;
-    this.abortController = abortController;
-    this.user = req.user.id;
-    this.req = req;
-    this.res = res;
-    this.debug = debug;
-    this.runs = new Map();
-    this.convos = new Map();
-  }
-
-  addRun(runId, runData) {
-    if (!this.runs.has(runId)) {
-      this.runs.set(runId, runData);
-      if (runData.conversationId) {
-        this.convos.set(runData.conversationId, runId);
-      }
-      return runData;
-    } else {
-      const existingData = this.runs.get(runId);
-      const update = { ...existingData, ...runData };
-      this.runs.set(runId, update);
-      if (update.conversationId) {
-        this.convos.set(update.conversationId, runId);
-      }
-      return update;
-    }
-  }
-
-  removeRun(runId) {
-    if (this.runs.has(runId)) {
-      this.runs.delete(runId);
-    } else {
-      logger.error(`[api/app/clients/llm/RunManager] Run with ID ${runId} does not exist.`);
-    }
-  }
-
-  getAllRuns() {
-    return Array.from(this.runs.values());
-  }
-
-  getRunById(runId) {
-    return this.runs.get(runId);
-  }
-
-  getRunByConversationId(conversationId) {
-    const runId = this.convos.get(conversationId);
-    return { run: this.runs.get(runId), runId };
-  }
-
-  createCallbacks(metadata) {
-    return [
-      {
-        handleChatModelStart: createStartHandler({ ...metadata, manager: this }),
-        handleLLMEnd: async (output, runId, _parentRunId) => {
-          const { llmOutput, ..._output } = output;
-          logger.debug(`[RunManager] handleLLMEnd: ${JSON.stringify(metadata)}`, {
-            runId,
-            _parentRunId,
-            llmOutput,
-          });
-
-          if (metadata.context !== 'title') {
-            logger.debug('[RunManager] handleLLMEnd:', {
-              output: _output,
-            });
-          }
-
-          const { tokenUsage } = output.llmOutput;
-          const run = this.getRunById(runId);
-          this.removeRun(runId);
-
-          const txData = {
-            user: this.user,
-            model: run?.model ?? 'gpt-3.5-turbo',
-            ...metadata,
-          };
-
-          await spendTokens(txData, tokenUsage);
-        },
-        handleLLMError: async (err) => {
-          logger.error(`[RunManager] handleLLMError: ${JSON.stringify(metadata)}`, err);
-          if (metadata.context === 'title') {
-            return;
-          } else if (metadata.context === 'plugins') {
-            throw new Error(err);
-          }
-          const { conversationId } = metadata;
-          const { run } = this.getRunByConversationId(conversationId);
-          if (run && run.error) {
-            const { error } = run;
-            throw new Error(error);
-          }
-        },
-      },
-    ];
-  }
-}
-
-module.exports = RunManager;

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

@@ -1,9 +1,5 @@
-const createLLM = require('./createLLM');
-const RunManager = require('./RunManager');
 const createCoherePayload = require('./createCoherePayload');
 
 module.exports = {
-  createLLM,
-  RunManager,
   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/prompts/createContextHandlers.js

@@ -1,6 +1,6 @@
 const axios = require('axios');
-const { isEnabled } = require('~/server/utils');
-const { logger } = require('~/config');
+const { logger } = require('@librechat/data-schemas');
+const { isEnabled, generateShortLivedToken } = require('@librechat/api');
 
 const footer = `Use the context as your learned knowledge to better answer the user.
 
@@ -18,7 +18,7 @@ function createContextHandlers(req, userMessageContent) {
   const queryPromises = [];
   const processedFiles = [];
   const processedIds = new Set();
-  const jwtToken = req.headers.authorization.split(' ')[1];
+  const jwtToken = generateShortLivedToken(req.user.id);
   const useFullContext = isEnabled(process.env.RAG_USE_FULL_CONTEXT);
 
   const query = async (file) => {

api/app/clients/prompts/formatMessages.js

@@ -237,41 +237,9 @@ const formatAgentMessages = (payload) => {
   return messages;
 };
 
-/**
- * Formats an array of messages for LangChain, making sure all content fields are strings
- * @param {Array<(HumanMessage|AIMessage|SystemMessage|ToolMessage)>} payload - The array of messages to format.
- * @returns {Array<(HumanMessage|AIMessage|SystemMessage|ToolMessage)>} - The array of formatted LangChain messages, including ToolMessages for tool calls.
- */
-const formatContentStrings = (payload) => {
-  const messages = [];
-
-  for (const message of payload) {
-    if (typeof message.content === 'string') {
-      continue;
-    }
-
-    if (!Array.isArray(message.content)) {
-      continue;
-    }
-
-    // Reduce text types to a single string, ignore all other types
-    const content = message.content.reduce((acc, curr) => {
-      if (curr.type === ContentTypes.TEXT) {
-        return `${acc}${curr[ContentTypes.TEXT]}\n`;
-      }
-      return acc;
-    }, '');
-
-    message.content = content.trim();
-  }
-
-  return messages;
-};
-
 module.exports = {
   formatMessage,
   formatFromLangChain,
   formatAgentMessages,
-  formatContentStrings,
   formatLangChainMessages,
 };

api/app/clients/specs/AnthropicClient.test.js

@@ -245,7 +245,7 @@ describe('AnthropicClient', () => {
     });
 
     describe('Claude 4 model headers', () => {
-      it('should add "prompt-caching" beta header for claude-sonnet-4 model', () => {
+      it('should add "prompt-caching" and "context-1m" beta headers for claude-sonnet-4 model', () => {
         const client = new AnthropicClient('test-api-key');
         const modelOptions = {
           model: 'claude-sonnet-4-20250514',
@@ -255,10 +255,30 @@ describe('AnthropicClient', () => {
         expect(anthropicClient._options.defaultHeaders).toBeDefined();
         expect(anthropicClient._options.defaultHeaders).toHaveProperty('anthropic-beta');
         expect(anthropicClient._options.defaultHeaders['anthropic-beta']).toBe(
-          'prompt-caching-2024-07-31',
+          'prompt-caching-2024-07-31,context-1m-2025-08-07',
         );
       });
 
+      it('should add "prompt-caching" and "context-1m" beta headers for claude-sonnet-4 model formats', () => {
+        const client = new AnthropicClient('test-api-key');
+        const modelVariations = [
+          'claude-sonnet-4-20250514',
+          'claude-sonnet-4-latest',
+          'anthropic/claude-sonnet-4-20250514',
+        ];
+
+        modelVariations.forEach((model) => {
+          const modelOptions = { model };
+          client.setOptions({ modelOptions, promptCache: true });
+          const anthropicClient = client.getClient(modelOptions);
+          expect(anthropicClient._options.defaultHeaders).toBeDefined();
+          expect(anthropicClient._options.defaultHeaders).toHaveProperty('anthropic-beta');
+          expect(anthropicClient._options.defaultHeaders['anthropic-beta']).toBe(
+            'prompt-caching-2024-07-31,context-1m-2025-08-07',
+          );
+        });
+      });
+
       it('should add "prompt-caching" beta header for claude-opus-4 model', () => {
         const client = new AnthropicClient('test-api-key');
         const modelOptions = {
@@ -273,20 +293,6 @@ describe('AnthropicClient', () => {
         );
       });
 
-      it('should add "prompt-caching" beta header for claude-4-sonnet model', () => {
-        const client = new AnthropicClient('test-api-key');
-        const modelOptions = {
-          model: 'claude-4-sonnet-20250514',
-        };
-        client.setOptions({ modelOptions, promptCache: true });
-        const anthropicClient = client.getClient(modelOptions);
-        expect(anthropicClient._options.defaultHeaders).toBeDefined();
-        expect(anthropicClient._options.defaultHeaders).toHaveProperty('anthropic-beta');
-        expect(anthropicClient._options.defaultHeaders['anthropic-beta']).toBe(
-          'prompt-caching-2024-07-31',
-        );
-      });
-
       it('should add "prompt-caching" beta header for claude-4-opus model', () => {
         const client = new AnthropicClient('test-api-key');
         const modelOptions = {

api/app/clients/specs/BaseClient.test.js

@@ -2,6 +2,14 @@ const { Constants } = require('librechat-data-provider');
 const { initializeFakeClient } = require('./FakeClient');
 
 jest.mock('~/db/connect');
+jest.mock('~/server/services/Config', () => ({
+  getAppConfig: jest.fn().mockResolvedValue({
+    // Default app config for tests
+    paths: { uploads: '/tmp' },
+    fileStrategy: 'local',
+    memory: { disabled: false },
+  }),
+}));
 jest.mock('~/models', () => ({
   User: jest.fn(),
   Key: jest.fn(),
@@ -422,6 +430,46 @@ describe('BaseClient', () => {
       expect(response).toEqual(expectedResult);
     });
 
+    test('should replace responseMessageId with new UUID when isRegenerate is true and messageId ends with underscore', async () => {
+      const mockCrypto = require('crypto');
+      const newUUID = 'new-uuid-1234';
+      jest.spyOn(mockCrypto, 'randomUUID').mockReturnValue(newUUID);
+
+      const opts = {
+        isRegenerate: true,
+        responseMessageId: 'existing-message-id_',
+      };
+
+      await TestClient.setMessageOptions(opts);
+
+      expect(TestClient.responseMessageId).toBe(newUUID);
+      expect(TestClient.responseMessageId).not.toBe('existing-message-id_');
+
+      mockCrypto.randomUUID.mockRestore();
+    });
+
+    test('should not replace responseMessageId when isRegenerate is false', async () => {
+      const opts = {
+        isRegenerate: false,
+        responseMessageId: 'existing-message-id_',
+      };
+
+      await TestClient.setMessageOptions(opts);
+
+      expect(TestClient.responseMessageId).toBe('existing-message-id_');
+    });
+
+    test('should not replace responseMessageId when it does not end with underscore', async () => {
+      const opts = {
+        isRegenerate: true,
+        responseMessageId: 'existing-message-id',
+      };
+
+      await TestClient.setMessageOptions(opts);
+
+      expect(TestClient.responseMessageId).toBe('existing-message-id');
+    });
+
     test('sendMessage should work with provided conversationId and parentMessageId', async () => {
       const userMessage = 'Second message in the conversation';
       const opts = {
@@ -539,6 +587,8 @@ describe('BaseClient', () => {
       expect(onStart).toHaveBeenCalledWith(
         expect.objectContaining({ text: 'Hello, world!' }),
         expect.any(String),
+        /** `isNewConvo` */
+        true,
       );
     });
 

api/app/clients/specs/FakeClient.js

@@ -1,5 +1,5 @@
+const { getModelMaxTokens } = require('@librechat/api');
 const BaseClient = require('../BaseClient');
-const { getModelMaxTokens } = require('../../../utils');
 
 class FakeClient extends BaseClient {
   constructor(apiKey, options = {}) {

api/app/clients/tools/index.js

@@ -1,4 +1,4 @@
-const availableTools = require('./manifest.json');
+const manifest = require('./manifest');
 
 // Structured Tools
 const DALLE3 = require('./structured/DALLE3');
@@ -13,23 +13,8 @@ const TraversaalSearch = require('./structured/TraversaalSearch');
 const createOpenAIImageTools = require('./structured/OpenAIImageTools');
 const TavilySearchResults = require('./structured/TavilySearchResults');
 
-/** @type {Record<string, TPlugin | undefined>} */
-const manifestToolMap = {};
-
-/** @type {Array<TPlugin>} */
-const toolkits = [];
-
-availableTools.forEach((tool) => {
-  manifestToolMap[tool.pluginKey] = tool;
-  if (tool.toolkit === true) {
-    toolkits.push(tool);
-  }
-});
-
 module.exports = {
-  toolkits,
-  availableTools,
-  manifestToolMap,
+  ...manifest,
   // Structured Tools
   DALLE3,
   FluxAPI,

api/app/clients/tools/manifest.js

@@ -0,0 +1,20 @@
+const availableTools = require('./manifest.json');
+
+/** @type {Record<string, TPlugin | undefined>} */
+const manifestToolMap = {};
+
+/** @type {Array<TPlugin>} */
+const toolkits = [];
+
+availableTools.forEach((tool) => {
+  manifestToolMap[tool.pluginKey] = tool;
+  if (tool.toolkit === true) {
+    toolkits.push(tool);
+  }
+});
+
+module.exports = {
+  toolkits,
+  availableTools,
+  manifestToolMap,
+};

api/app/clients/tools/manifest.json

@@ -49,7 +49,7 @@
     "pluginKey": "image_gen_oai",
     "toolkit": true,
     "description": "Image Generation and Editing using OpenAI's latest state-of-the-art models",
-    "icon": "/assets/image_gen_oai.png",
+    "icon": "assets/image_gen_oai.png",
     "authConfig": [
       {
         "authField": "IMAGE_GEN_OAI_API_KEY",
@@ -75,7 +75,7 @@
     "name": "Browser",
     "pluginKey": "web-browser",
     "description": "Scrape and summarize webpage data",
-    "icon": "/assets/web-browser.svg",
+    "icon": "assets/web-browser.svg",
     "authConfig": [
       {
         "authField": "OPENAI_API_KEY",
@@ -170,7 +170,7 @@
     "name": "OpenWeather",
     "pluginKey": "open_weather",
     "description": "Get weather forecasts and historical data from the OpenWeather API",
-    "icon": "/assets/openweather.png",
+    "icon": "assets/openweather.png",
     "authConfig": [
       {
         "authField": "OPENWEATHER_API_KEY",

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

@@ -1,14 +1,13 @@
 const { z } = require('zod');
 const path = require('path');
 const OpenAI = require('openai');
-const fetch = require('node-fetch');
 const { v4: uuidv4 } = require('uuid');
+const { ProxyAgent, fetch } = require('undici');
 const { Tool } = require('@langchain/core/tools');
-const { HttpsProxyAgent } = require('https-proxy-agent');
+const { logger } = require('@librechat/data-schemas');
+const { getImageBasename } = require('@librechat/api');
 const { FileContext, ContentTypes } = require('librechat-data-provider');
-const { getImageBasename } = require('~/server/services/Files/images');
 const extractBaseURL = require('~/utils/extractBaseURL');
-const logger = require('~/config/winston');
 
 const displayMessage =
   "DALL-E 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.";
@@ -46,7 +45,10 @@ class DALLE3 extends Tool {
     }
 
     if (process.env.PROXY) {
-      config.httpAgent = new HttpsProxyAgent(process.env.PROXY);
+      const proxyAgent = new ProxyAgent(process.env.PROXY);
+      config.fetchOptions = {
+        dispatcher: proxyAgent,
+      };
     }
 
     /** @type {OpenAI} */
@@ -163,7 +165,8 @@ Error Message: ${error.message}`);
     if (this.isAgent) {
       let fetchOptions = {};
       if (process.env.PROXY) {
-        fetchOptions.agent = new HttpsProxyAgent(process.env.PROXY);
+        const proxyAgent = new ProxyAgent(process.env.PROXY);
+        fetchOptions.dispatcher = proxyAgent;
       }
       const imageResponse = await fetch(theImageUrl, fetchOptions);
       const arrayBuffer = await imageResponse.arrayBuffer();

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

@@ -1,69 +1,17 @@
-const { z } = require('zod');
 const axios = require('axios');
 const { v4 } = require('uuid');
 const OpenAI = require('openai');
 const FormData = require('form-data');
+const { ProxyAgent } = require('undici');
 const { tool } = require('@langchain/core/tools');
-const { logAxiosError } = require('@librechat/api');
 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');
-const { extractBaseURL } = require('~/utils');
+const extractBaseURL = require('~/utils/extractBaseURL');
 const { getFiles } = require('~/models/File');
 
-/** Default descriptions for image generation tool  */
-const DEFAULT_IMAGE_GEN_DESCRIPTION = `
-Generates high-quality, original images based solely on text, not using any uploaded reference images.
-
-When to use \`image_gen_oai\`:
-- To create entirely new images from detailed text descriptions that do NOT reference any image files.
-
-When NOT to use \`image_gen_oai\`:
-- If the user has uploaded any images and requests modifications, enhancements, or remixing based on those uploads → use \`image_edit_oai\` instead.
-
-Generated image IDs will be returned in the response, so you can refer to them in future requests made to \`image_edit_oai\`.
-`.trim();
-
-/** Default description for image editing tool  */
-const DEFAULT_IMAGE_EDIT_DESCRIPTION =
-  `Generates high-quality, original images based on text and one or more uploaded/referenced images.
-
-When to use \`image_edit_oai\`:
-- The user wants to modify, extend, or remix one **or more** uploaded images, either:
-- Previously generated, or in the current request (both to be included in the \`image_ids\` array).
-- Always when the user refers to uploaded images for editing, enhancement, remixing, style transfer, or combining elements.
-- Any current or existing images are to be used as visual guides.
-- If there are any files in the current request, they are more likely than not expected as references for image edit requests.
-
-When NOT to use \`image_edit_oai\`:
-- Brand-new generations that do not rely on an existing image → use \`image_gen_oai\` instead.
-
-Both generated and referenced image IDs will be returned in the response, so you can refer to them in future requests made to \`image_edit_oai\`.
-`.trim();
-
-/** Default prompt descriptions  */
-const DEFAULT_IMAGE_GEN_PROMPT_DESCRIPTION = `Describe the image you want in detail. 
-      Be highly specific—break your idea into layers: 
-      (1) main concept and subject,
-      (2) composition and position,
-      (3) lighting and mood,
-      (4) style, medium, or camera details,
-      (5) important features (age, expression, clothing, etc.),
-      (6) background.
-      Use positive, descriptive language and specify what should be included, not what to avoid. 
-      List number and characteristics of people/objects, and mention style/technical requirements (e.g., "DSLR photo, 85mm lens, golden hour").
-      Do not reference any uploaded images—use for new image creation from text only.`;
-
-const DEFAULT_IMAGE_EDIT_PROMPT_DESCRIPTION = `Describe the changes, enhancements, or new ideas to apply to the uploaded image(s).
-      Be highly specific—break your request into layers: 
-      (1) main concept or transformation,
-      (2) specific edits/replacements or composition guidance,
-      (3) desired style, mood, or technique,
-      (4) features/items to keep, change, or add (such as objects, people, clothing, lighting, etc.).
-      Use positive, descriptive language and clarify what should be included or changed, not what to avoid.
-      Always base this prompt on the most recently uploaded reference images.`;
-
 const displayMessage =
   "The tool 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.";
 
@@ -91,22 +39,6 @@ function returnValue(value) {
   return value;
 }
 
-const getImageGenDescription = () => {
-  return process.env.IMAGE_GEN_OAI_DESCRIPTION || DEFAULT_IMAGE_GEN_DESCRIPTION;
-};
-
-const getImageEditDescription = () => {
-  return process.env.IMAGE_EDIT_OAI_DESCRIPTION || DEFAULT_IMAGE_EDIT_DESCRIPTION;
-};
-
-const getImageGenPromptDescription = () => {
-  return process.env.IMAGE_GEN_OAI_PROMPT_DESCRIPTION || DEFAULT_IMAGE_GEN_PROMPT_DESCRIPTION;
-};
-
-const getImageEditPromptDescription = () => {
-  return process.env.IMAGE_EDIT_OAI_PROMPT_DESCRIPTION || DEFAULT_IMAGE_EDIT_PROMPT_DESCRIPTION;
-};
-
 function createAbortHandler() {
   return function () {
     logger.debug('[ImageGenOAI] Image generation aborted');
@@ -121,7 +53,9 @@ function createAbortHandler() {
  * @param {string} fields.IMAGE_GEN_OAI_API_KEY - The OpenAI API key
  * @param {boolean} [fields.override] - Whether to override the API key check, necessary for app initialization
  * @param {MongoFile[]} [fields.imageFiles] - The images to be used for editing
- * @returns {Array} - Array of image tools
+ * @param {string} [fields.imageOutputType] - The image output type configuration
+ * @param {string} [fields.fileStrategy] - The file storage strategy
+ * @returns {Array<ReturnType<tool>>} - Array of image tools
  */
 function createOpenAIImageTools(fields = {}) {
   /** @type {boolean} Used to initialize the Tool without necessary variables. */
@@ -131,8 +65,8 @@ function createOpenAIImageTools(fields = {}) {
     throw new Error('This tool is only available for agents.');
   }
   const { req } = fields;
-  const imageOutputType = req?.app.locals.imageOutputType || EImageOutputType.PNG;
-  const appFileStrategy = req?.app.locals.fileStrategy;
+  const imageOutputType = fields.imageOutputType || EImageOutputType.PNG;
+  const appFileStrategy = fields.fileStrategy;
 
   const getApiKey = () => {
     const apiKey = process.env.IMAGE_GEN_OAI_API_KEY ?? '';
@@ -189,7 +123,10 @@ function createOpenAIImageTools(fields = {}) {
       }
       const clientConfig = { ...closureConfig };
       if (process.env.PROXY) {
-        clientConfig.httpAgent = new HttpsProxyAgent(process.env.PROXY);
+        const proxyAgent = new ProxyAgent(process.env.PROXY);
+        clientConfig.fetchOptions = {
+          dispatcher: proxyAgent,
+        };
       }
 
       /** @type {OpenAI} */
@@ -282,46 +219,7 @@ Error Message: ${error.message}`);
       ];
       return [response, { content, file_ids }];
     },
-    {
-      name: 'image_gen_oai',
-      description: getImageGenDescription(),
-      schema: z.object({
-        prompt: z.string().max(32000).describe(getImageGenPromptDescription()),
-        background: z
-          .enum(['transparent', 'opaque', 'auto'])
-          .optional()
-          .describe(
-            'Sets transparency for the background. Must be one of transparent, opaque or auto (default). When transparent, the output format should be png or webp.',
-          ),
-        /*
-        n: z
-          .number()
-          .int()
-          .min(1)
-          .max(10)
-          .optional()
-          .describe('The number of images to generate. Must be between 1 and 10.'),
-        output_compression: z
-          .number()
-          .int()
-          .min(0)
-          .max(100)
-          .optional()
-          .describe('The compression level (0-100%) for webp or jpeg formats. Defaults to 100.'),
-           */
-        quality: z
-          .enum(['auto', 'high', 'medium', 'low'])
-          .optional()
-          .describe('The quality of the image. One of auto (default), high, medium, or low.'),
-        size: z
-          .enum(['auto', '1024x1024', '1536x1024', '1024x1536'])
-          .optional()
-          .describe(
-            'The size of the generated image. One of 1024x1024, 1536x1024 (landscape), 1024x1536 (portrait), or auto (default).',
-          ),
-      }),
-      responseFormat: 'content_and_artifact',
-    },
+    oaiToolkit.image_gen_oai,
   );
 
   /**
@@ -335,7 +233,10 @@ Error Message: ${error.message}`);
 
       const clientConfig = { ...closureConfig };
       if (process.env.PROXY) {
-        clientConfig.httpAgent = new HttpsProxyAgent(process.env.PROXY);
+        const proxyAgent = new ProxyAgent(process.env.PROXY);
+        clientConfig.fetchOptions = {
+          dispatcher: proxyAgent,
+        };
       }
 
       const formData = new FormData();
@@ -447,6 +348,10 @@ Error Message: ${error.message}`);
           baseURL,
         };
 
+        if (process.env.PROXY) {
+          axiosConfig.httpsAgent = new HttpsProxyAgent(process.env.PROXY);
+        }
+
         if (process.env.IMAGE_GEN_OAI_AZURE_API_VERSION && process.env.IMAGE_GEN_OAI_BASEURL) {
           axiosConfig.params = {
             'api-version': process.env.IMAGE_GEN_OAI_AZURE_API_VERSION,
@@ -498,48 +403,7 @@ Error Message: ${error.message || 'Unknown error'}`);
         }
       }
     },
-    {
-      name: 'image_edit_oai',
-      description: getImageEditDescription(),
-      schema: z.object({
-        image_ids: z
-          .array(z.string())
-          .min(1)
-          .describe(
-            `
-IDs (image ID strings) of previously generated or uploaded images that should guide the edit.
-
-Guidelines:
-- If the user's request depends on any prior image(s), copy their image IDs into the \`image_ids\` array (in the same order the user refers to them).  
-- Never invent or hallucinate IDs; only use IDs that are still visible in the conversation context.
-- If no earlier image is relevant, omit the field entirely.
-`.trim(),
-          ),
-        prompt: z.string().max(32000).describe(getImageEditPromptDescription()),
-        /*
-        n: z
-          .number()
-          .int()
-          .min(1)
-          .max(10)
-          .optional()
-          .describe('The number of images to generate. Must be between 1 and 10. Defaults to 1.'),
-        */
-        quality: z
-          .enum(['auto', 'high', 'medium', 'low'])
-          .optional()
-          .describe(
-            'The quality of the image. One of auto (default), high, medium, or low. High/medium/low only supported for gpt-image-1.',
-          ),
-        size: z
-          .enum(['auto', '1024x1024', '1536x1024', '1024x1536', '256x256', '512x512'])
-          .optional()
-          .describe(
-            'The size of the generated images. For gpt-image-1: auto (default), 1024x1024, 1536x1024, 1024x1536. For dall-e-2: 256x256, 512x512, 1024x1024.',
-          ),
-      }),
-      responseFormat: 'content_and_artifact',
-    },
+    oaiToolkit.image_edit_oai,
   );
 
   return [imageGenTool, imageEditTool];

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

@@ -6,19 +6,19 @@ 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.';
+  "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.";
 
 class StableDiffusionAPI extends Tool {
   constructor(fields) {
     super();
     /** @type {string} User ID */
     this.userId = fields.userId;
-    /** @type {Express.Request | undefined} Express Request object, only provided by ToolService */
+    /** @type {ServerRequest | undefined} Express Request object, only provided by ToolService */
     this.req = fields.req;
     /** @type {boolean} Used to initialize the Tool without necessary variables. */
     this.override = fields.override ?? false;
@@ -44,7 +44,7 @@ class StableDiffusionAPI extends Tool {
 // "negative_prompt":"semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, out of frame, low quality, ugly, mutation, deformed"
 // - Generate images only once per human query unless explicitly requested by the user`;
     this.description =
-      'You can generate images using text with \'stable-diffusion\'. This tool is exclusively for visual content.';
+      "You can generate images using text with 'stable-diffusion'. This tool is exclusively for visual content.";
     this.schema = z.object({
       prompt: z
         .string()

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/structured/YouTube.js

@@ -1,9 +1,9 @@
-const { z } = require('zod');
+const { ytToolkit } = require('@librechat/api');
 const { tool } = require('@langchain/core/tools');
 const { youtube } = require('@googleapis/youtube');
+const { logger } = require('@librechat/data-schemas');
 const { YoutubeTranscript } = require('youtube-transcript');
 const { getApiKey } = require('./credentials');
-const { logger } = require('~/config');
 
 function extractVideoId(url) {
   const rawIdRegex = /^[a-zA-Z0-9_-]{11}$/;
@@ -29,7 +29,7 @@ function parseTranscript(transcriptResponse) {
     .map((entry) => entry.text.trim())
     .filter((text) => text)
     .join(' ')
-    .replaceAll(''', '\'');
+    .replaceAll(''', "'");
 }
 
 function createYouTubeTools(fields = {}) {
@@ -42,160 +42,94 @@ function createYouTubeTools(fields = {}) {
     auth: apiKey,
   });
 
-  const searchTool = tool(
-    async ({ query, maxResults = 5 }) => {
-      const response = await youtubeClient.search.list({
-        part: 'snippet',
-        q: query,
-        type: 'video',
-        maxResults: maxResults || 5,
-      });
-      const result = response.data.items.map((item) => ({
-        title: item.snippet.title,
-        description: item.snippet.description,
-        url: `https://www.youtube.com/watch?v=${item.id.videoId}`,
-      }));
-      return JSON.stringify(result, null, 2);
-    },
-    {
-      name: 'youtube_search',
-      description: `Search for YouTube videos by keyword or phrase.
-- Required: query (search terms to find videos)
-- Optional: maxResults (number of videos to return, 1-50, default: 5)
-- Returns: List of videos with titles, descriptions, and URLs
-- Use for: Finding specific videos, exploring content, research
-Example: query="cooking pasta tutorials" maxResults=3`,
-      schema: z.object({
-        query: z.string().describe('Search query terms'),
-        maxResults: z.number().int().min(1).max(50).optional().describe('Number of results (1-50)'),
-      }),
-    },
-  );
+  const searchTool = tool(async ({ query, maxResults = 5 }) => {
+    const response = await youtubeClient.search.list({
+      part: 'snippet',
+      q: query,
+      type: 'video',
+      maxResults: maxResults || 5,
+    });
+    const result = response.data.items.map((item) => ({
+      title: item.snippet.title,
+      description: item.snippet.description,
+      url: `https://www.youtube.com/watch?v=${item.id.videoId}`,
+    }));
+    return JSON.stringify(result, null, 2);
+  }, ytToolkit.youtube_search);
 
-  const infoTool = tool(
-    async ({ url }) => {
-      const videoId = extractVideoId(url);
-      if (!videoId) {
-        throw new Error('Invalid YouTube URL or video ID');
-      }
+  const infoTool = tool(async ({ url }) => {
+    const videoId = extractVideoId(url);
+    if (!videoId) {
+      throw new Error('Invalid YouTube URL or video ID');
+    }
 
-      const response = await youtubeClient.videos.list({
-        part: 'snippet,statistics',
-        id: videoId,
-      });
+    const response = await youtubeClient.videos.list({
+      part: 'snippet,statistics',
+      id: videoId,
+    });
 
-      if (!response.data.items?.length) {
-        throw new Error('Video not found');
-      }
-      const video = response.data.items[0];
+    if (!response.data.items?.length) {
+      throw new Error('Video not found');
+    }
+    const video = response.data.items[0];
 
-      const result = {
-        title: video.snippet.title,
-        description: video.snippet.description,
-        views: video.statistics.viewCount,
-        likes: video.statistics.likeCount,
-        comments: video.statistics.commentCount,
-      };
-      return JSON.stringify(result, null, 2);
-    },
-    {
-      name: 'youtube_info',
-      description: `Get detailed metadata and statistics for a specific YouTube video.
-- Required: url (full YouTube URL or video ID)
-- Returns: Video title, description, view count, like count, comment count
-- Use for: Getting video metrics and basic metadata
-- DO NOT USE FOR VIDEO SUMMARIES, USE TRANSCRIPTS FOR COMPREHENSIVE ANALYSIS
-- Accepts both full URLs and video IDs
-Example: url="https://youtube.com/watch?v=abc123" or url="abc123"`,
-      schema: z.object({
-        url: z.string().describe('YouTube video URL or ID'),
-      }),
-    },
-  );
+    const result = {
+      title: video.snippet.title,
+      description: video.snippet.description,
+      views: video.statistics.viewCount,
+      likes: video.statistics.likeCount,
+      comments: video.statistics.commentCount,
+    };
+    return JSON.stringify(result, null, 2);
+  }, ytToolkit.youtube_info);
 
-  const commentsTool = tool(
-    async ({ url, maxResults = 10 }) => {
-      const videoId = extractVideoId(url);
-      if (!videoId) {
-        throw new Error('Invalid YouTube URL or video ID');
-      }
+  const commentsTool = tool(async ({ url, maxResults = 10 }) => {
+    const videoId = extractVideoId(url);
+    if (!videoId) {
+      throw new Error('Invalid YouTube URL or video ID');
+    }
 
-      const response = await youtubeClient.commentThreads.list({
-        part: 'snippet',
-        videoId,
-        maxResults: maxResults || 10,
-      });
+    const response = await youtubeClient.commentThreads.list({
+      part: 'snippet',
+      videoId,
+      maxResults: maxResults || 10,
+    });
 
-      const result = response.data.items.map((item) => ({
-        author: item.snippet.topLevelComment.snippet.authorDisplayName,
-        text: item.snippet.topLevelComment.snippet.textDisplay,
-        likes: item.snippet.topLevelComment.snippet.likeCount,
-      }));
-      return JSON.stringify(result, null, 2);
-    },
-    {
-      name: 'youtube_comments',
-      description: `Retrieve top-level comments from a YouTube video.
-- Required: url (full YouTube URL or video ID)
-- Optional: maxResults (number of comments, 1-50, default: 10)
-- Returns: Comment text, author names, like counts
-- Use for: Sentiment analysis, audience feedback, engagement review
-Example: url="abc123" maxResults=20`,
-      schema: z.object({
-        url: z.string().describe('YouTube video URL or ID'),
-        maxResults: z
-          .number()
-          .int()
-          .min(1)
-          .max(50)
-          .optional()
-          .describe('Number of comments to retrieve'),
-      }),
-    },
-  );
+    const result = response.data.items.map((item) => ({
+      author: item.snippet.topLevelComment.snippet.authorDisplayName,
+      text: item.snippet.topLevelComment.snippet.textDisplay,
+      likes: item.snippet.topLevelComment.snippet.likeCount,
+    }));
+    return JSON.stringify(result, null, 2);
+  }, ytToolkit.youtube_comments);
 
-  const transcriptTool = tool(
-    async ({ url }) => {
-      const videoId = extractVideoId(url);
-      if (!videoId) {
-        throw new Error('Invalid YouTube URL or video ID');
+  const transcriptTool = tool(async ({ url }) => {
+    const videoId = extractVideoId(url);
+    if (!videoId) {
+      throw new Error('Invalid YouTube URL or video ID');
+    }
+
+    try {
+      try {
+        const transcript = await YoutubeTranscript.fetchTranscript(videoId, { lang: 'en' });
+        return parseTranscript(transcript);
+      } catch (e) {
+        logger.error(e);
       }
 
       try {
-        try {
-          const transcript = await YoutubeTranscript.fetchTranscript(videoId, { lang: 'en' });
-          return parseTranscript(transcript);
-        } catch (e) {
-          logger.error(e);
-        }
-
-        try {
-          const transcript = await YoutubeTranscript.fetchTranscript(videoId, { lang: 'de' });
-          return parseTranscript(transcript);
-        } catch (e) {
-          logger.error(e);
-        }
-
-        const transcript = await YoutubeTranscript.fetchTranscript(videoId);
+        const transcript = await YoutubeTranscript.fetchTranscript(videoId, { lang: 'de' });
         return parseTranscript(transcript);
-      } catch (error) {
-        throw new Error(`Failed to fetch transcript: ${error.message}`);
+      } catch (e) {
+        logger.error(e);
       }
-    },
-    {
-      name: 'youtube_transcript',
-      description: `Fetch and parse the transcript/captions of a YouTube video.
-- Required: url (full YouTube URL or video ID)
-- Returns: Full video transcript as plain text
-- Use for: Content analysis, summarization, translation reference
-- This is the "Go-to" tool for analyzing actual video content
-- Attempts to fetch English first, then German, then any available language
-Example: url="https://youtube.com/watch?v=abc123"`,
-      schema: z.object({
-        url: z.string().describe('YouTube video URL or ID'),
-      }),
-    },
-  );
+
+      const transcript = await YoutubeTranscript.fetchTranscript(videoId);
+      return parseTranscript(transcript);
+    } catch (error) {
+      throw new Error(`Failed to fetch transcript: ${error.message}`);
+    }
+  }, ytToolkit.youtube_transcript);
 
   return [searchTool, infoTool, commentsTool, transcriptTool];
 }

api/app/clients/tools/structured/specs/DALLE3-proxy.spec.js

@@ -0,0 +1,60 @@
+const DALLE3 = require('../DALLE3');
+const { ProxyAgent } = require('undici');
+
+jest.mock('tiktoken');
+const processFileURL = jest.fn();
+
+describe('DALLE3 Proxy Configuration', () => {
+  let originalEnv;
+
+  beforeAll(() => {
+    originalEnv = { ...process.env };
+  });
+
+  beforeEach(() => {
+    jest.resetModules();
+    process.env = { ...originalEnv };
+  });
+
+  afterEach(() => {
+    process.env = originalEnv;
+  });
+
+  it('should configure ProxyAgent in fetchOptions.dispatcher when PROXY env is set', () => {
+    // Set proxy environment variable
+    process.env.PROXY = 'http://proxy.example.com:8080';
+    process.env.DALLE_API_KEY = 'test-api-key';
+
+    // Create instance
+    const dalleWithProxy = new DALLE3({ processFileURL });
+
+    // Check that the openai client exists
+    expect(dalleWithProxy.openai).toBeDefined();
+
+    // Check that _options exists and has fetchOptions with a dispatcher
+    expect(dalleWithProxy.openai._options).toBeDefined();
+    expect(dalleWithProxy.openai._options.fetchOptions).toBeDefined();
+    expect(dalleWithProxy.openai._options.fetchOptions.dispatcher).toBeDefined();
+    expect(dalleWithProxy.openai._options.fetchOptions.dispatcher).toBeInstanceOf(ProxyAgent);
+  });
+
+  it('should not configure ProxyAgent when PROXY env is not set', () => {
+    // Ensure PROXY is not set
+    delete process.env.PROXY;
+    process.env.DALLE_API_KEY = 'test-api-key';
+
+    // Create instance
+    const dalleWithoutProxy = new DALLE3({ processFileURL });
+
+    // Check that the openai client exists
+    expect(dalleWithoutProxy.openai).toBeDefined();
+
+    // Check that _options exists but fetchOptions either doesn't exist or doesn't have a dispatcher
+    expect(dalleWithoutProxy.openai._options).toBeDefined();
+
+    // fetchOptions should either not exist or not have a dispatcher
+    if (dalleWithoutProxy.openai._options.fetchOptions) {
+      expect(dalleWithoutProxy.openai._options.fetchOptions.dispatcher).toBeUndefined();
+    }
+  });
+});

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

@@ -1,9 +1,8 @@
 const OpenAI = require('openai');
+const { logger } = require('@librechat/data-schemas');
 const DALLE3 = require('../DALLE3');
-const logger = require('~/config/winston');
 
 jest.mock('openai');
-
 jest.mock('@librechat/data-schemas', () => {
   return {
     logger: {
@@ -26,25 +25,6 @@ jest.mock('tiktoken', () => {
 
 const processFileURL = jest.fn();
 
-jest.mock('~/server/services/Files/images', () => ({
-  getImageBasename: jest.fn().mockImplementation((url) => {
-    // Split the URL by '/'
-    const parts = url.split('/');
-
-    // Get the last part of the URL
-    const lastPart = parts.pop();
-
-    // Check if the last part of the URL matches the image extension regex
-    const imageExtensionRegex = /\.(jpg|jpeg|png|gif|bmp|tiff|svg)$/i;
-    if (imageExtensionRegex.test(lastPart)) {
-      return lastPart;
-    }
-
-    // If the regex test fails, return an empty string
-    return '';
-  }),
-}));
-
 const generate = jest.fn();
 OpenAI.mockImplementation(() => ({
   images: {

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

@@ -1,26 +1,46 @@
 const { z } = require('zod');
 const axios = require('axios');
 const { tool } = require('@langchain/core/tools');
+const { logger } = require('@librechat/data-schemas');
+const { generateShortLivedToken } = require('@librechat/api');
 const { Tools, EToolResources } = require('librechat-data-provider');
+const { filterFilesByAgentAccess } = require('~/server/services/Files/permissions');
 const { getFiles } = require('~/models/File');
-const { logger } = require('~/config');
 
 /**
  *
  * @param {Object} options
  * @param {ServerRequest} options.req
  * @param {Agent['tool_resources']} options.tool_resources
+ * @param {string} [options.agentId] - The agent ID for file access control
  * @returns {Promise<{
  *   files: Array<{ file_id: string; filename: string }>,
  *   toolContext: string
  * }>}
  */
 const primeFiles = async (options) => {
-  const { tool_resources } = options;
+  const { tool_resources, req, agentId } = options;
   const file_ids = tool_resources?.[EToolResources.file_search]?.file_ids ?? [];
   const agentResourceIds = new Set(file_ids);
   const resourceFiles = tool_resources?.[EToolResources.file_search]?.files ?? [];
-  const dbFiles = ((await getFiles({ file_id: { $in: file_ids } })) ?? []).concat(resourceFiles);
+
+  // Get all files first
+  const allFiles = (await getFiles({ file_id: { $in: file_ids } }, null, { text: 0 })) ?? [];
+
+  // Filter by access if user and agent are provided
+  let dbFiles;
+  if (req?.user?.id && agentId) {
+    dbFiles = await filterFilesByAgentAccess({
+      files: allFiles,
+      userId: req.user.id,
+      role: req.user.role,
+      agentId,
+    });
+  } else {
+    dbFiles = allFiles;
+  }
+
+  dbFiles = dbFiles.concat(resourceFiles);
 
   let toolContext = `- Note: Semantic search is available through the ${Tools.file_search} tool but no files are currently loaded. Request the user to upload documents to search through.`;
 
@@ -48,18 +68,19 @@ const primeFiles = async (options) => {
 /**
  *
  * @param {Object} options
- * @param {ServerRequest} options.req
+ * @param {string} options.userId
  * @param {Array<{ file_id: string; filename: string }>} options.files
  * @param {string} [options.entity_id]
+ * @param {boolean} [options.fileCitations=false] - Whether to include citation instructions
  * @returns
  */
-const createFileSearchTool = async ({ req, files, entity_id }) => {
+const createFileSearchTool = async ({ userId, files, entity_id, fileCitations = false }) => {
   return tool(
     async ({ query }) => {
       if (files.length === 0) {
         return 'No files to search. Instruct the user to add files for the search.';
       }
-      const jwtToken = req.headers.authorization.split(' ')[1];
+      const jwtToken = generateShortLivedToken(userId);
       if (!jwtToken) {
         return 'There was an error authenticating the file search request.';
       }
@@ -105,11 +126,13 @@ const createFileSearchTool = async ({ req, files, entity_id }) => {
       }
 
       const formattedResults = validResults
-        .flatMap((result) =>
+        .flatMap((result, fileIndex) =>
           result.data.map(([docInfo, distance]) => ({
             filename: docInfo.metadata.source.split('/').pop(),
             content: docInfo.page_content,
             distance,
+            file_id: files[fileIndex]?.file_id,
+            page: docInfo.metadata.page || null,
           })),
         )
         // TODO: results should be sorted by relevance, not distance
@@ -119,18 +142,41 @@ const createFileSearchTool = async ({ req, files, entity_id }) => {
 
       const formattedString = formattedResults
         .map(
-          (result) =>
-            `File: ${result.filename}\nRelevance: ${1.0 - result.distance.toFixed(4)}\nContent: ${
-              result.content
-            }\n`,
+          (result, index) =>
+            `File: ${result.filename}${
+              fileCitations ? `\nAnchor: \\ue202turn0file${index} (${result.filename})` : ''
+            }\nRelevance: ${(1.0 - result.distance).toFixed(4)}\nContent: ${result.content}\n`,
         )
         .join('\n---\n');
 
-      return formattedString;
+      const sources = formattedResults.map((result) => ({
+        type: 'file',
+        fileId: result.file_id,
+        content: result.content,
+        fileName: result.filename,
+        relevance: 1.0 - result.distance,
+        pages: result.page ? [result.page] : [],
+        pageRelevance: result.page ? { [result.page]: 1.0 - result.distance } : {},
+      }));
+
+      return [formattedString, { [Tools.file_search]: { sources, fileCitations } }];
     },
     {
       name: Tools.file_search,
-      description: `Performs semantic search across attached "${Tools.file_search}" documents using natural language queries. This tool analyzes the content of uploaded files to find relevant information, quotes, and passages that best match your query. Use this to extract specific information or find relevant sections within the available documents.`,
+      responseFormat: 'content_and_artifact',
+      description: `Performs semantic search across attached "${Tools.file_search}" documents using natural language queries. This tool analyzes the content of uploaded files to find relevant information, quotes, and passages that best match your query. Use this to extract specific information or find relevant sections within the available documents.${
+        fileCitations
+          ? `
+
+**CITE FILE SEARCH RESULTS:**
+Use anchor markers immediately after statements derived from file content. Reference the filename in your text:
+- File citation: "The document.pdf states that... \\ue202turn0file0"  
+- Page reference: "According to report.docx... \\ue202turn0file1"
+- Multi-file: "Multiple sources confirm... \\ue200\\ue202turn0file0\\ue202turn0file1\\ue201"
+
+**ALWAYS mention the filename in your text before the citation marker. NEVER use markdown links or footnotes.**`
+          : ''
+      }`,
       schema: z.object({
         query: z
           .string()

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

@@ -1,12 +1,19 @@
-const { mcpToolPattern } = require('@librechat/api');
 const { logger } = require('@librechat/data-schemas');
 const { SerpAPI } = require('@langchain/community/tools/serpapi');
 const { Calculator } = require('@langchain/community/tools/calculator');
 const { EnvVar, createCodeExecutionTool, createSearchTool } = require('@librechat/agents');
 const {
-  Tools,
-  EToolResources,
+  checkAccess,
+  createSafeUser,
+  mcpToolPattern,
   loadWebSearchAuth,
+} = require('@librechat/api');
+const {
+  Tools,
+  Constants,
+  Permissions,
+  EToolResources,
+  PermissionTypes,
   replaceSpecialVars,
 } = require('librechat-data-provider');
 const {
@@ -29,9 +36,10 @@ const {
 const { primeFiles: primeCodeFiles } = require('~/server/services/Files/Code/process');
 const { createFileSearchTool, primeFiles: primeSearchFiles } = require('./fileSearch');
 const { getUserPluginAuthValue } = require('~/server/services/PluginService');
+const { createMCPTool, createMCPTools } = require('~/server/services/MCP');
 const { loadAuthValues } = require('~/server/services/Tools/credentials');
-const { getCachedTools } = require('~/server/services/Config');
-const { createMCPTool } = require('~/server/services/MCP');
+const { getMCPServerTools } = require('~/server/services/Config');
+const { getRoleByName } = require('~/models/Role');
 
 /**
  * Validates the availability and authentication of tools for a user based on environment variables or user-specific plugin authentication values.
@@ -126,27 +134,37 @@ const getAuthFields = (toolKey) => {
 
 /**
  *
- * @param {object} object
- * @param {string} object.user
- * @param {Pick<Agent, 'id' | 'provider' | 'model'>} [object.agent]
- * @param {string} [object.model]
- * @param {EModelEndpoint} [object.endpoint]
- * @param {LoadToolOptions} [object.options]
- * @param {boolean} [object.useSpecs]
- * @param {Array<string>} object.tools
- * @param {boolean} [object.functions]
- * @param {boolean} [object.returnMap]
+ * @param {object} params
+ * @param {string} params.user
+ * @param {Record<string, Record<string, string>>} [object.userMCPAuthMap]
+ * @param {AbortSignal} [object.signal]
+ * @param {Pick<Agent, 'id' | 'provider' | 'model'>} [params.agent]
+ * @param {string} [params.model]
+ * @param {EModelEndpoint} [params.endpoint]
+ * @param {LoadToolOptions} [params.options]
+ * @param {boolean} [params.useSpecs]
+ * @param {Array<string>} params.tools
+ * @param {boolean} [params.functions]
+ * @param {boolean} [params.returnMap]
+ * @param {AppConfig['webSearch']} [params.webSearch]
+ * @param {AppConfig['fileStrategy']} [params.fileStrategy]
+ * @param {AppConfig['imageOutputType']} [params.imageOutputType]
  * @returns {Promise<{ loadedTools: Tool[], toolContextMap: Object<string, any> } | Record<string,Tool>>}
  */
 const loadTools = async ({
   user,
   agent,
   model,
+  signal,
   endpoint,
+  userMCPAuthMap,
   tools = [],
   options = {},
   functions = true,
   returnMap = false,
+  webSearch,
+  fileStrategy,
+  imageOutputType,
 }) => {
   const toolConstructors = {
     flux: FluxAPI,
@@ -205,6 +223,8 @@ const loadTools = async ({
         ...authValues,
         isAgent: !!agent,
         req: options.req,
+        imageOutputType,
+        fileStrategy,
         imageFiles,
       });
     },
@@ -220,7 +240,7 @@ const loadTools = async ({
   const imageGenOptions = {
     isAgent: !!agent,
     req: options.req,
-    fileStrategy: options.fileStrategy,
+    fileStrategy,
     processFileURL: options.processFileURL,
     returnMetadata: options.returnMetadata,
     uploadImageBuffer: options.uploadImageBuffer,
@@ -235,7 +255,7 @@ const loadTools = async ({
 
   /** @type {Record<string, string>} */
   const toolContextMap = {};
-  const appTools = (await getCachedTools({ includeGlobal: true })) ?? {};
+  const requestedMCPTools = {};
 
   for (const tool of tools) {
     if (tool === Tools.execute_code) {
@@ -245,7 +265,13 @@ const loadTools = async ({
           authFields: [EnvVar.CODE_API_KEY],
         });
         const codeApiKey = authValues[EnvVar.CODE_API_KEY];
-        const { files, toolContext } = await primeCodeFiles(options, codeApiKey);
+        const { files, toolContext } = await primeCodeFiles(
+          {
+            ...options,
+            agentId: agent?.id,
+          },
+          codeApiKey,
+        );
         if (toolContext) {
           toolContextMap[tool] = toolContext;
         }
@@ -260,19 +286,43 @@ const loadTools = async ({
       continue;
     } else if (tool === Tools.file_search) {
       requestedTools[tool] = async () => {
-        const { files, toolContext } = await primeSearchFiles(options);
+        const { files, toolContext } = await primeSearchFiles({
+          ...options,
+          agentId: agent?.id,
+        });
         if (toolContext) {
           toolContextMap[tool] = toolContext;
         }
-        return createFileSearchTool({ req: options.req, files, entity_id: agent?.id });
+
+        /** @type {boolean | undefined} Check if user has FILE_CITATIONS permission */
+        let fileCitations;
+        if (fileCitations == null && options.req?.user != null) {
+          try {
+            fileCitations = await checkAccess({
+              user: options.req.user,
+              permissionType: PermissionTypes.FILE_CITATIONS,
+              permissions: [Permissions.USE],
+              getRoleByName,
+            });
+          } catch (error) {
+            logger.error('[handleTools] FILE_CITATIONS permission check failed:', error);
+            fileCitations = false;
+          }
+        }
+
+        return createFileSearchTool({
+          userId: user,
+          files,
+          entity_id: agent?.id,
+          fileCitations,
+        });
       };
       continue;
     } else if (tool === Tools.web_search) {
-      const webSearchConfig = options?.req?.app?.locals?.webSearch;
       const result = await loadWebSearchAuth({
         userId: user,
         loadAuthValues,
-        webSearchConfig,
+        webSearchConfig: webSearch,
       });
       const { onSearchResults, onGetHighlights } = options?.[Tools.web_search] ?? {};
       requestedTools[tool] = async () => {
@@ -294,15 +344,34 @@ Current Date & Time: ${replaceSpecialVars({ text: '{{iso_datetime}}' })}
         });
       };
       continue;
-    } else if (tool && appTools[tool] && mcpToolPattern.test(tool)) {
-      requestedTools[tool] = async () =>
-        createMCPTool({
-          req: options.req,
-          res: options.res,
-          toolKey: tool,
-          model: agent?.model ?? model,
-          provider: agent?.provider ?? endpoint,
-        });
+    } else if (tool && mcpToolPattern.test(tool)) {
+      const [toolName, serverName] = tool.split(Constants.mcp_delimiter);
+      if (toolName === Constants.mcp_server) {
+        /** Placeholder used for UI purposes */
+        continue;
+      }
+      if (serverName && options.req?.config?.mcpConfig?.[serverName] == null) {
+        logger.warn(
+          `MCP server "${serverName}" for "${toolName}" tool is not configured${agent?.id != null && agent.id ? ` but attached to "${agent.id}"` : ''}`,
+        );
+        continue;
+      }
+      if (toolName === Constants.mcp_all) {
+        requestedMCPTools[serverName] = [
+          {
+            type: 'all',
+            serverName,
+          },
+        ];
+        continue;
+      }
+
+      requestedMCPTools[serverName] = requestedMCPTools[serverName] || [];
+      requestedMCPTools[serverName].push({
+        type: 'single',
+        toolKey: tool,
+        serverName,
+      });
       continue;
     }
 
@@ -342,6 +411,75 @@ Current Date & Time: ${replaceSpecialVars({ text: '{{iso_datetime}}' })}
   }
 
   const loadedTools = (await Promise.all(toolPromises)).flatMap((plugin) => plugin || []);
+  const mcpToolPromises = [];
+  /** MCP server tools are initialized sequentially by server */
+  let index = -1;
+  const failedMCPServers = new Set();
+  const safeUser = createSafeUser(options.req?.user);
+  for (const [serverName, toolConfigs] of Object.entries(requestedMCPTools)) {
+    index++;
+    /** @type {LCAvailableTools} */
+    let availableTools;
+    for (const config of toolConfigs) {
+      try {
+        if (failedMCPServers.has(serverName)) {
+          continue;
+        }
+        const mcpParams = {
+          index,
+          signal,
+          user: safeUser,
+          userMCPAuthMap,
+          res: options.res,
+          model: agent?.model ?? model,
+          serverName: config.serverName,
+          provider: agent?.provider ?? endpoint,
+        };
+
+        if (config.type === 'all' && toolConfigs.length === 1) {
+          /** Handle async loading for single 'all' tool config */
+          mcpToolPromises.push(
+            createMCPTools(mcpParams).catch((error) => {
+              logger.error(`Error loading ${serverName} tools:`, error);
+              return null;
+            }),
+          );
+          continue;
+        }
+        if (!availableTools) {
+          try {
+            availableTools = await getMCPServerTools(safeUser.id, serverName);
+          } catch (error) {
+            logger.error(`Error fetching available tools for MCP server ${serverName}:`, error);
+          }
+        }
+
+        /** Handle synchronous loading */
+        const mcpTool =
+          config.type === 'all'
+            ? await createMCPTools(mcpParams)
+            : await createMCPTool({
+                ...mcpParams,
+                availableTools,
+                toolKey: config.toolKey,
+              });
+
+        if (Array.isArray(mcpTool)) {
+          loadedTools.push(...mcpTool);
+        } else if (mcpTool) {
+          loadedTools.push(mcpTool);
+        } else {
+          failedMCPServers.add(serverName);
+          logger.warn(
+            `MCP tool creation failed for "${config.toolKey}", server may be unavailable or unauthenticated.`,
+          );
+        }
+      } catch (error) {
+        logger.error(`Error loading MCP tool for server ${serverName}:`, error);
+      }
+    }
+  }
+  loadedTools.push(...(await Promise.all(mcpToolPromises)).flatMap((plugin) => plugin || []));
   return { loadedTools, toolContextMap };
 };
 

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

@@ -9,7 +9,27 @@ const mockPluginService = {
 
 jest.mock('~/server/services/PluginService', () => mockPluginService);
 
-const { BaseLLM } = require('@langchain/openai');
+jest.mock('~/server/services/Config', () => ({
+  getAppConfig: jest.fn().mockResolvedValue({
+    // Default app config for tool tests
+    paths: { uploads: '/tmp' },
+    fileStrategy: 'local',
+    filteredTools: [],
+    includedTools: [],
+  }),
+  getCachedTools: jest.fn().mockResolvedValue({
+    // Default cached tools for tests
+    dalle: {
+      type: 'function',
+      function: {
+        name: 'dalle',
+        description: 'DALL-E image generation',
+        parameters: {},
+      },
+    },
+  }),
+}));
+
 const { Calculator } = require('@langchain/community/tools/calculator');
 
 const { User } = require('~/db/models');
@@ -151,7 +171,6 @@ describe('Tool Handlers', () => {
     beforeAll(async () => {
       const toolMap = await loadTools({
         user: fakeUser._id,
-        model: BaseLLM,
         tools: sampleTools,
         returnMap: true,
         useSpecs: true,
@@ -245,7 +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,
       });
@@ -255,7 +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/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

@@ -1,113 +1,56 @@
 const { Keyv } = require('keyv');
-const { isEnabled, math } = require('@librechat/api');
-const { CacheKeys, ViolationTypes, Time } = require('librechat-data-provider');
-const { logFile, violationFile } = require('./keyvFiles');
-const keyvRedis = require('./keyvRedis');
-const keyvMongo = require('./keyvMongo');
-
-const { BAN_DURATION, USE_REDIS, DEBUG_MEMORY_CACHE, CI } = process.env ?? {};
-
-const duration = math(BAN_DURATION, 7200000);
-const isRedisEnabled = isEnabled(USE_REDIS);
-const debugMemoryCache = isEnabled(DEBUG_MEMORY_CACHE);
-
-const createViolationInstance = (namespace) => {
-  const config = isRedisEnabled ? { store: keyvRedis } : { store: violationFile, namespace };
-  return new Keyv(config);
-};
-
-// Serve cache from memory so no need to clear it on startup/exit
-const pending_req = isRedisEnabled
-  ? new Keyv({ store: keyvRedis })
-  : new Keyv({ namespace: CacheKeys.PENDING_REQ });
-
-const config = isRedisEnabled
-  ? new Keyv({ store: keyvRedis })
-  : new Keyv({ namespace: CacheKeys.CONFIG_STORE });
-
-const roles = isRedisEnabled
-  ? new Keyv({ store: keyvRedis })
-  : new Keyv({ namespace: CacheKeys.ROLES });
-
-const mcpTools = isRedisEnabled
-  ? new Keyv({ store: keyvRedis })
-  : new Keyv({ namespace: CacheKeys.MCP_TOOLS });
-
-const audioRuns = isRedisEnabled
-  ? new Keyv({ store: keyvRedis, ttl: Time.TEN_MINUTES })
-  : new Keyv({ namespace: CacheKeys.AUDIO_RUNS, ttl: Time.TEN_MINUTES });
-
-const messages = isRedisEnabled
-  ? new Keyv({ store: keyvRedis, ttl: Time.ONE_MINUTE })
-  : new Keyv({ namespace: CacheKeys.MESSAGES, ttl: Time.ONE_MINUTE });
-
-const flows = isRedisEnabled
-  ? new Keyv({ store: keyvRedis, ttl: Time.TWO_MINUTES })
-  : new Keyv({ namespace: CacheKeys.FLOWS, ttl: Time.ONE_MINUTE * 3 });
-
-const tokenConfig = isRedisEnabled
-  ? new Keyv({ store: keyvRedis, ttl: Time.THIRTY_MINUTES })
-  : new Keyv({ namespace: CacheKeys.TOKEN_CONFIG, ttl: Time.THIRTY_MINUTES });
-
-const genTitle = isRedisEnabled
-  ? new Keyv({ store: keyvRedis, ttl: Time.TWO_MINUTES })
-  : new Keyv({ namespace: CacheKeys.GEN_TITLE, ttl: Time.TWO_MINUTES });
-
-const s3ExpiryInterval = isRedisEnabled
-  ? new Keyv({ store: keyvRedis, ttl: Time.THIRTY_MINUTES })
-  : new Keyv({ namespace: CacheKeys.S3_EXPIRY_INTERVAL, ttl: Time.THIRTY_MINUTES });
-
-const modelQueries = isEnabled(process.env.USE_REDIS)
-  ? new Keyv({ store: keyvRedis })
-  : new Keyv({ namespace: CacheKeys.MODEL_QUERIES });
-
-const abortKeys = isRedisEnabled
-  ? new Keyv({ store: keyvRedis })
-  : new Keyv({ namespace: CacheKeys.ABORT_KEYS, ttl: Time.TEN_MINUTES });
-
-const openIdExchangedTokensCache = isRedisEnabled
-  ? new Keyv({ store: keyvRedis, ttl: Time.TEN_MINUTES })
-  : new Keyv({ namespace: CacheKeys.OPENID_EXCHANGED_TOKENS, ttl: Time.TEN_MINUTES });
+const { Time, CacheKeys, ViolationTypes } = require('librechat-data-provider');
+const {
+  logFile,
+  keyvMongo,
+  cacheConfig,
+  sessionCache,
+  standardCache,
+  violationCache,
+} = require('@librechat/api');
 
 const namespaces = {
-  [CacheKeys.ROLES]: roles,
-  [CacheKeys.MCP_TOOLS]: mcpTools,
-  [CacheKeys.CONFIG_STORE]: config,
-  [CacheKeys.PENDING_REQ]: pending_req,
-  [ViolationTypes.BAN]: new Keyv({ store: keyvMongo, namespace: CacheKeys.BANS, ttl: duration }),
-  [CacheKeys.ENCODED_DOMAINS]: new Keyv({
+  [ViolationTypes.GENERAL]: new Keyv({ store: logFile, namespace: 'violations' }),
+  [ViolationTypes.LOGINS]: violationCache(ViolationTypes.LOGINS),
+  [ViolationTypes.CONCURRENT]: violationCache(ViolationTypes.CONCURRENT),
+  [ViolationTypes.NON_BROWSER]: violationCache(ViolationTypes.NON_BROWSER),
+  [ViolationTypes.MESSAGE_LIMIT]: violationCache(ViolationTypes.MESSAGE_LIMIT),
+  [ViolationTypes.REGISTRATIONS]: violationCache(ViolationTypes.REGISTRATIONS),
+  [ViolationTypes.TOKEN_BALANCE]: violationCache(ViolationTypes.TOKEN_BALANCE),
+  [ViolationTypes.TTS_LIMIT]: violationCache(ViolationTypes.TTS_LIMIT),
+  [ViolationTypes.STT_LIMIT]: violationCache(ViolationTypes.STT_LIMIT),
+  [ViolationTypes.CONVO_ACCESS]: violationCache(ViolationTypes.CONVO_ACCESS),
+  [ViolationTypes.TOOL_CALL_LIMIT]: violationCache(ViolationTypes.TOOL_CALL_LIMIT),
+  [ViolationTypes.FILE_UPLOAD_LIMIT]: violationCache(ViolationTypes.FILE_UPLOAD_LIMIT),
+  [ViolationTypes.VERIFY_EMAIL_LIMIT]: violationCache(ViolationTypes.VERIFY_EMAIL_LIMIT),
+  [ViolationTypes.RESET_PASSWORD_LIMIT]: violationCache(ViolationTypes.RESET_PASSWORD_LIMIT),
+  [ViolationTypes.ILLEGAL_MODEL_REQUEST]: violationCache(ViolationTypes.ILLEGAL_MODEL_REQUEST),
+  [ViolationTypes.BAN]: new Keyv({
     store: keyvMongo,
-    namespace: CacheKeys.ENCODED_DOMAINS,
-    ttl: 0,
+    namespace: CacheKeys.BANS,
+    ttl: cacheConfig.BAN_DURATION,
   }),
-  general: new Keyv({ store: logFile, namespace: 'violations' }),
-  concurrent: createViolationInstance('concurrent'),
-  non_browser: createViolationInstance('non_browser'),
-  message_limit: createViolationInstance('message_limit'),
-  token_balance: createViolationInstance(ViolationTypes.TOKEN_BALANCE),
-  registrations: createViolationInstance('registrations'),
-  [ViolationTypes.TTS_LIMIT]: createViolationInstance(ViolationTypes.TTS_LIMIT),
-  [ViolationTypes.STT_LIMIT]: createViolationInstance(ViolationTypes.STT_LIMIT),
-  [ViolationTypes.CONVO_ACCESS]: createViolationInstance(ViolationTypes.CONVO_ACCESS),
-  [ViolationTypes.TOOL_CALL_LIMIT]: createViolationInstance(ViolationTypes.TOOL_CALL_LIMIT),
-  [ViolationTypes.FILE_UPLOAD_LIMIT]: createViolationInstance(ViolationTypes.FILE_UPLOAD_LIMIT),
-  [ViolationTypes.VERIFY_EMAIL_LIMIT]: createViolationInstance(ViolationTypes.VERIFY_EMAIL_LIMIT),
-  [ViolationTypes.RESET_PASSWORD_LIMIT]: createViolationInstance(
-    ViolationTypes.RESET_PASSWORD_LIMIT,
+
+  [CacheKeys.OPENID_SESSION]: sessionCache(CacheKeys.OPENID_SESSION),
+  [CacheKeys.SAML_SESSION]: sessionCache(CacheKeys.SAML_SESSION),
+
+  [CacheKeys.ROLES]: standardCache(CacheKeys.ROLES),
+  [CacheKeys.APP_CONFIG]: standardCache(CacheKeys.APP_CONFIG),
+  [CacheKeys.CONFIG_STORE]: standardCache(CacheKeys.CONFIG_STORE),
+  [CacheKeys.PENDING_REQ]: standardCache(CacheKeys.PENDING_REQ),
+  [CacheKeys.ENCODED_DOMAINS]: new Keyv({ store: keyvMongo, namespace: CacheKeys.ENCODED_DOMAINS }),
+  [CacheKeys.ABORT_KEYS]: standardCache(CacheKeys.ABORT_KEYS, Time.TEN_MINUTES),
+  [CacheKeys.TOKEN_CONFIG]: standardCache(CacheKeys.TOKEN_CONFIG, Time.THIRTY_MINUTES),
+  [CacheKeys.GEN_TITLE]: standardCache(CacheKeys.GEN_TITLE, Time.TWO_MINUTES),
+  [CacheKeys.S3_EXPIRY_INTERVAL]: standardCache(CacheKeys.S3_EXPIRY_INTERVAL, Time.THIRTY_MINUTES),
+  [CacheKeys.MODEL_QUERIES]: standardCache(CacheKeys.MODEL_QUERIES),
+  [CacheKeys.AUDIO_RUNS]: standardCache(CacheKeys.AUDIO_RUNS, Time.TEN_MINUTES),
+  [CacheKeys.MESSAGES]: standardCache(CacheKeys.MESSAGES, Time.ONE_MINUTE),
+  [CacheKeys.FLOWS]: standardCache(CacheKeys.FLOWS, Time.ONE_MINUTE * 3),
+  [CacheKeys.OPENID_EXCHANGED_TOKENS]: standardCache(
+    CacheKeys.OPENID_EXCHANGED_TOKENS,
+    Time.TEN_MINUTES,
   ),
-  [ViolationTypes.ILLEGAL_MODEL_REQUEST]: createViolationInstance(
-    ViolationTypes.ILLEGAL_MODEL_REQUEST,
-  ),
-  logins: createViolationInstance('logins'),
-  [CacheKeys.ABORT_KEYS]: abortKeys,
-  [CacheKeys.TOKEN_CONFIG]: tokenConfig,
-  [CacheKeys.GEN_TITLE]: genTitle,
-  [CacheKeys.S3_EXPIRY_INTERVAL]: s3ExpiryInterval,
-  [CacheKeys.MODEL_QUERIES]: modelQueries,
-  [CacheKeys.AUDIO_RUNS]: audioRuns,
-  [CacheKeys.MESSAGES]: messages,
-  [CacheKeys.FLOWS]: flows,
-  [CacheKeys.OPENID_EXCHANGED_TOKENS]: openIdExchangedTokensCache,
 };
 
 /**
@@ -116,7 +59,10 @@ const namespaces = {
  */
 function getTTLStores() {
   return Object.values(namespaces).filter(
-    (store) => store instanceof Keyv && typeof store.opts?.ttl === 'number' && store.opts.ttl > 0,
+    (store) =>
+      store instanceof Keyv &&
+      parseInt(store.opts?.ttl ?? '0') > 0 &&
+      !store.opts?.store?.constructor?.name?.includes('Redis'), // Only include non-Redis stores
   );
 }
 
@@ -152,18 +98,18 @@ async function clearExpiredFromCache(cache) {
       if (data?.expires && data.expires <= expiryTime) {
         const deleted = await cache.opts.store.delete(key);
         if (!deleted) {
-          debugMemoryCache &&
+          cacheConfig.DEBUG_MEMORY_CACHE &&
             console.warn(`[Cache] Error deleting entry: ${key} from ${cache.opts.namespace}`);
           continue;
         }
         cleared++;
       }
     } catch (error) {
-      debugMemoryCache &&
+      cacheConfig.DEBUG_MEMORY_CACHE &&
         console.log(`[Cache] Error processing entry from ${cache.opts.namespace}:`, error);
       const deleted = await cache.opts.store.delete(key);
       if (!deleted) {
-        debugMemoryCache &&
+        cacheConfig.DEBUG_MEMORY_CACHE &&
           console.warn(`[Cache] Error deleting entry: ${key} from ${cache.opts.namespace}`);
         continue;
       }
@@ -172,7 +118,7 @@ async function clearExpiredFromCache(cache) {
   }
 
   if (cleared > 0) {
-    debugMemoryCache &&
+    cacheConfig.DEBUG_MEMORY_CACHE &&
       console.log(
         `[Cache] Cleared ${cleared} entries older than ${ttl}ms from ${cache.opts.namespace}`,
       );
@@ -213,7 +159,7 @@ async function clearAllExpiredFromCache() {
   }
 }
 
-if (!isRedisEnabled && !isEnabled(CI)) {
+if (!cacheConfig.USE_REDIS && !cacheConfig.CI) {
   /** @type {Set<NodeJS.Timeout>} */
   const cleanupIntervals = new Set();
 
@@ -224,7 +170,7 @@ if (!isRedisEnabled && !isEnabled(CI)) {
 
   cleanupIntervals.add(cleanup);
 
-  if (debugMemoryCache) {
+  if (cacheConfig.DEBUG_MEMORY_CACHE) {
     const monitor = setInterval(() => {
       const ttlStores = getTTLStores();
       const memory = process.memoryUsage();
@@ -245,13 +191,13 @@ if (!isRedisEnabled && !isEnabled(CI)) {
   }
 
   const dispose = () => {
-    debugMemoryCache && console.log('[Cache] Cleaning up and shutting down...');
+    cacheConfig.DEBUG_MEMORY_CACHE && console.log('[Cache] Cleaning up and shutting down...');
     cleanupIntervals.forEach((interval) => clearInterval(interval));
     cleanupIntervals.clear();
 
     // One final cleanup before exit
     clearAllExpiredFromCache().then(() => {
-      debugMemoryCache && console.log('[Cache] Final cleanup completed');
+      cacheConfig.DEBUG_MEMORY_CACHE && console.log('[Cache] Final cleanup completed');
       process.exit(0);
     });
   };

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/ioredisClient.js

@@ -1,92 +0,0 @@
-const fs = require('fs');
-const Redis = require('ioredis');
-const { isEnabled } = require('~/server/utils');
-const logger = require('~/config/winston');
-
-const { REDIS_URI, USE_REDIS, USE_REDIS_CLUSTER, REDIS_CA, REDIS_MAX_LISTENERS } = process.env;
-
-/** @type {import('ioredis').Redis | import('ioredis').Cluster} */
-let ioredisClient;
-const redis_max_listeners = Number(REDIS_MAX_LISTENERS) || 40;
-
-function mapURI(uri) {
-  const regex =
-    /^(?:(?<scheme>\w+):\/\/)?(?:(?<user>[^:@]+)(?::(?<password>[^@]+))?@)?(?<host>[\w.-]+)(?::(?<port>\d{1,5}))?$/;
-  const match = uri.match(regex);
-
-  if (match) {
-    const { scheme, user, password, host, port } = match.groups;
-
-    return {
-      scheme: scheme || 'none',
-      user: user || null,
-      password: password || null,
-      host: host || null,
-      port: port || null,
-    };
-  } else {
-    const parts = uri.split(':');
-    if (parts.length === 2) {
-      return {
-        scheme: 'none',
-        user: null,
-        password: null,
-        host: parts[0],
-        port: parts[1],
-      };
-    }
-
-    return {
-      scheme: 'none',
-      user: null,
-      password: null,
-      host: uri,
-      port: null,
-    };
-  }
-}
-
-if (REDIS_URI && isEnabled(USE_REDIS)) {
-  let redisOptions = null;
-
-  if (REDIS_CA) {
-    const ca = fs.readFileSync(REDIS_CA);
-    redisOptions = { tls: { ca } };
-  }
-
-  if (isEnabled(USE_REDIS_CLUSTER)) {
-    const hosts = REDIS_URI.split(',').map((item) => {
-      var value = mapURI(item);
-
-      return {
-        host: value.host,
-        port: value.port,
-      };
-    });
-    ioredisClient = new Redis.Cluster(hosts, { redisOptions });
-  } else {
-    ioredisClient = new Redis(REDIS_URI, redisOptions);
-  }
-
-  ioredisClient.on('ready', () => {
-    logger.info('IoRedis connection ready');
-  });
-  ioredisClient.on('reconnecting', () => {
-    logger.info('IoRedis connection reconnecting');
-  });
-  ioredisClient.on('end', () => {
-    logger.info('IoRedis connection ended');
-  });
-  ioredisClient.on('close', () => {
-    logger.info('IoRedis connection closed');
-  });
-  ioredisClient.on('error', (err) => logger.error('IoRedis connection error:', err));
-  ioredisClient.setMaxListeners(redis_max_listeners);
-  logger.info(
-    '[Optional] IoRedis initialized for rate limiters. If you have issues, disable Redis or restart the server.',
-  );
-} else {
-  logger.info('[Optional] IoRedis not initialized for rate limiters.');
-}
-
-module.exports = ioredisClient;

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/keyvRedis.js

@@ -1,109 +0,0 @@
-const fs = require('fs');
-const ioredis = require('ioredis');
-const KeyvRedis = require('@keyv/redis').default;
-const { isEnabled } = require('~/server/utils');
-const logger = require('~/config/winston');
-
-const { REDIS_URI, USE_REDIS, USE_REDIS_CLUSTER, REDIS_CA, REDIS_KEY_PREFIX, REDIS_MAX_LISTENERS } =
-  process.env;
-
-let keyvRedis;
-const redis_prefix = REDIS_KEY_PREFIX || '';
-const redis_max_listeners = Number(REDIS_MAX_LISTENERS) || 40;
-
-function mapURI(uri) {
-  const regex =
-    /^(?:(?<scheme>\w+):\/\/)?(?:(?<user>[^:@]+)(?::(?<password>[^@]+))?@)?(?<host>[\w.-]+)(?::(?<port>\d{1,5}))?$/;
-  const match = uri.match(regex);
-
-  if (match) {
-    const { scheme, user, password, host, port } = match.groups;
-
-    return {
-      scheme: scheme || 'none',
-      user: user || null,
-      password: password || null,
-      host: host || null,
-      port: port || null,
-    };
-  } else {
-    const parts = uri.split(':');
-    if (parts.length === 2) {
-      return {
-        scheme: 'none',
-        user: null,
-        password: null,
-        host: parts[0],
-        port: parts[1],
-      };
-    }
-
-    return {
-      scheme: 'none',
-      user: null,
-      password: null,
-      host: uri,
-      port: null,
-    };
-  }
-}
-
-if (REDIS_URI && isEnabled(USE_REDIS)) {
-  let redisOptions = null;
-  /** @type {import('@keyv/redis').KeyvRedisOptions} */
-  let keyvOpts = {
-    useRedisSets: false,
-    keyPrefix: redis_prefix,
-  };
-
-  if (REDIS_CA) {
-    const ca = fs.readFileSync(REDIS_CA);
-    redisOptions = { tls: { ca } };
-  }
-
-  if (isEnabled(USE_REDIS_CLUSTER)) {
-    const hosts = REDIS_URI.split(',').map((item) => {
-      var value = mapURI(item);
-
-      return {
-        host: value.host,
-        port: value.port,
-      };
-    });
-    const cluster = new ioredis.Cluster(hosts, { redisOptions });
-    keyvRedis = new KeyvRedis(cluster, keyvOpts);
-  } else {
-    keyvRedis = new KeyvRedis(REDIS_URI, keyvOpts);
-  }
-
-  const pingInterval = setInterval(
-    () => {
-      logger.debug('KeyvRedis ping');
-      keyvRedis.client.ping().catch((err) => logger.error('Redis keep-alive ping failed:', err));
-    },
-    5 * 60 * 1000,
-  );
-
-  keyvRedis.on('ready', () => {
-    logger.info('KeyvRedis connection ready');
-  });
-  keyvRedis.on('reconnecting', () => {
-    logger.info('KeyvRedis connection reconnecting');
-  });
-  keyvRedis.on('end', () => {
-    logger.info('KeyvRedis connection ended');
-  });
-  keyvRedis.on('close', () => {
-    clearInterval(pingInterval);
-    logger.info('KeyvRedis connection closed');
-  });
-  keyvRedis.on('error', (err) => logger.error('KeyvRedis connection error:', err));
-  keyvRedis.setMaxListeners(redis_max_listeners);
-  logger.info(
-    '[Optional] Redis initialized. If you have issues, or seeing older values, disable it or flush cache to refresh values.',
-  );
-} else {
-  logger.info('[Optional] Redis not initialized.');
-}
-
-module.exports = keyvRedis;

api/cache/logViolation.js

@@ -1,4 +1,5 @@
-const { isEnabled } = require('~/server/utils');
+const { isEnabled } = require('@librechat/api');
+const { ViolationTypes } = require('librechat-data-provider');
 const getLogStores = require('./getLogStores');
 const banViolation = require('./banViolation');
 
@@ -9,14 +10,14 @@ const banViolation = require('./banViolation');
  * @param {Object} res - Express response object.
  * @param {string} type - The type of violation.
  * @param {Object} errorMessage - The error message to log.
- * @param {number} [score=1] - The severity of the violation. Defaults to 1
+ * @param {number | string} [score=1] - The severity of the violation. Defaults to 1
  */
 const logViolation = async (req, res, type, errorMessage, score = 1) => {
   const userId = req.user?.id ?? req.user?._id;
   if (!userId) {
     return;
   }
-  const logs = getLogStores('general');
+  const logs = getLogStores(ViolationTypes.GENERAL);
   const violationLogs = getLogStores(type);
   const key = isEnabled(process.env.USE_REDIS) ? `${type}:${userId}` : userId;
 

api/config/index.js

@@ -1,27 +1,13 @@
 const { EventSource } = require('eventsource');
 const { Time } = require('librechat-data-provider');
-const { MCPManager, FlowStateManager } = require('@librechat/api');
+const { MCPManager, FlowStateManager, OAuthReconnectionManager } = require('@librechat/api');
 const logger = require('./winston');
 
 global.EventSource = EventSource;
 
 /** @type {MCPManager} */
-let mcpManager = null;
 let flowManager = null;
 
-/**
- * @param {string} [userId] - Optional user ID, to avoid disconnecting the current user.
- * @returns {MCPManager}
- */
-function getMCPManager(userId) {
-  if (!mcpManager) {
-    mcpManager = MCPManager.getInstance();
-  } else {
-    mcpManager.checkIdleConnections(userId);
-  }
-  return mcpManager;
-}
-
 /**
  * @param {Keyv} flowsCache
  * @returns {FlowStateManager}
@@ -37,6 +23,9 @@ function getFlowStateManager(flowsCache) {
 
 module.exports = {
   logger,
-  getMCPManager,
+  createMCPManager: MCPManager.createInstance,
+  getMCPManager: MCPManager.getInstance,
   getFlowStateManager,
+  createOAuthReconnectionManager: OAuthReconnectionManager.createInstance,
+  getOAuthReconnectionManager: OAuthReconnectionManager.getInstance,
 };

api/db/connect.js

@@ -1,11 +1,34 @@
 require('dotenv').config();
+const { isEnabled } = require('@librechat/api');
+const { logger } = require('@librechat/data-schemas');
+
 const mongoose = require('mongoose');
 const MONGO_URI = process.env.MONGO_URI;
 
 if (!MONGO_URI) {
   throw new Error('Please define the MONGO_URI environment variable');
 }
+/** The maximum number of connections in the connection pool. */
+const maxPoolSize = parseInt(process.env.MONGO_MAX_POOL_SIZE) || undefined;
+/** The minimum number of connections in the connection pool. */
+const minPoolSize = parseInt(process.env.MONGO_MIN_POOL_SIZE) || undefined;
+/** The maximum number of connections that may be in the process of being established concurrently by the connection pool. */
+const maxConnecting = parseInt(process.env.MONGO_MAX_CONNECTING) || undefined;
+/** The maximum number of milliseconds that a connection can remain idle in the pool before being removed and closed. */
+const maxIdleTimeMS = parseInt(process.env.MONGO_MAX_IDLE_TIME_MS) || undefined;
+/** The maximum time in milliseconds that a thread can wait for a connection to become available. */
+const waitQueueTimeoutMS = parseInt(process.env.MONGO_WAIT_QUEUE_TIMEOUT_MS) || undefined;
+/** Set to false to disable automatic index creation for all models associated with this connection. */
+const autoIndex =
+  process.env.MONGO_AUTO_INDEX != undefined
+    ? isEnabled(process.env.MONGO_AUTO_INDEX) || false
+    : undefined;
 
+/** Set to `false` to disable Mongoose automatically calling `createCollection()` on every model created on this connection. */
+const autoCreate =
+  process.env.MONGO_AUTO_CREATE != undefined
+    ? isEnabled(process.env.MONGO_AUTO_CREATE) || false
+    : undefined;
 /**
  * Global is used here to maintain a cached connection across hot reloads
  * in development. This prevents connections growing exponentially
@@ -26,13 +49,21 @@ async function connectDb() {
   if (!cached.promise || disconnected) {
     const opts = {
       bufferCommands: false,
+      ...(maxPoolSize ? { maxPoolSize } : {}),
+      ...(minPoolSize ? { minPoolSize } : {}),
+      ...(maxConnecting ? { maxConnecting } : {}),
+      ...(maxIdleTimeMS ? { maxIdleTimeMS } : {}),
+      ...(waitQueueTimeoutMS ? { waitQueueTimeoutMS } : {}),
+      ...(autoIndex != undefined ? { autoIndex } : {}),
+      ...(autoCreate != undefined ? { autoCreate } : {}),
       // useNewUrlParser: true,
       // useUnifiedTopology: true,
       // bufferMaxEntries: 0,
       // useFindAndModify: true,
       // useCreateIndex: true
     };
-
+    logger.info('Mongo Connection options');
+    logger.info(JSON.stringify(opts, null, 2));
     mongoose.set('strictQuery', true);
     cached.promise = mongoose.connect(MONGO_URI, opts).then((mongoose) => {
       return mongoose;

api/db/indexSync.js

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

api/jest.config.js

@@ -3,6 +3,7 @@ module.exports = {
   clearMocks: true,
   roots: ['<rootDir>'],
   coverageDirectory: 'coverage',
+  testTimeout: 30000, // 30 seconds timeout for all tests
   setupFiles: [
     './test/jestSetup.js',
     './test/__mocks__/logger.js',

api/models/Agent.js

@@ -1,18 +1,17 @@
 const mongoose = require('mongoose');
 const crypto = require('node:crypto');
 const { logger } = require('@librechat/data-schemas');
-const { SystemRoles, Tools, actionDelimiter } = require('librechat-data-provider');
-const { GLOBAL_PROJECT_NAME, EPHEMERAL_AGENT_ID, mcp_delimiter } =
+const { ResourceType, SystemRoles, Tools, actionDelimiter } = require('librechat-data-provider');
+const { GLOBAL_PROJECT_NAME, EPHEMERAL_AGENT_ID, mcp_all, mcp_delimiter } =
   require('librechat-data-provider').Constants;
-const { CONFIG_STORE, STARTUP_CONFIG } = require('librechat-data-provider').CacheKeys;
 const {
-  getProjectByName,
-  addAgentIdsToProject,
-  removeAgentIdsFromProject,
   removeAgentFromAllProjects,
+  removeAgentIdsFromProject,
+  addAgentIdsToProject,
+  getProjectByName,
 } = require('./Project');
-const { getCachedTools } = require('~/server/services/Config');
-const getLogStores = require('~/cache/getLogStores');
+const { removeAllPermissions } = require('~/server/services/PermissionService');
+const { getMCPServerTools } = require('~/server/services/Config');
 const { getActions } = require('./Action');
 const { Agent } = require('~/db/models');
 
@@ -23,7 +22,7 @@ const { Agent } = require('~/db/models');
  * @throws {Error} If the agent creation fails.
  */
 const createAgent = async (agentData) => {
-  const { author, ...versionData } = agentData;
+  const { author: _author, ...versionData } = agentData;
   const timestamp = new Date();
   const initialAgentData = {
     ...agentData,
@@ -34,7 +33,9 @@ const createAgent = async (agentData) => {
         updatedAt: timestamp,
       },
     ],
+    category: agentData.category || 'general',
   };
+
   return (await Agent.create(initialAgentData)).toObject();
 };
 
@@ -48,49 +49,73 @@ const createAgent = async (agentData) => {
  */
 const getAgent = async (searchParameter) => await Agent.findOne(searchParameter).lean();
 
+/**
+ * Get multiple agent documents based on the provided search parameters.
+ *
+ * @param {Object} searchParameter - The search parameters to find agents.
+ * @returns {Promise<Agent[]>} Array of agent documents as plain objects.
+ */
+const getAgents = async (searchParameter) => await Agent.find(searchParameter).lean();
+
 /**
  * Load an agent based on the provided ID
  *
  * @param {Object} params
  * @param {ServerRequest} params.req
+ * @param {string} params.spec
  * @param {string} params.agent_id
  * @param {string} params.endpoint
  * @param {import('@librechat/agents').ClientOptions} [params.model_parameters]
  * @returns {Promise<Agent|null>} The agent document as a plain object, or null if not found.
  */
-const loadEphemeralAgent = async ({ req, agent_id, endpoint, model_parameters: _m }) => {
+const loadEphemeralAgent = async ({ req, spec, agent_id, endpoint, model_parameters: _m }) => {
   const { model, ...model_parameters } = _m;
-  /** @type {Record<string, FunctionTool>} */
-  const availableTools = await getCachedTools({ includeGlobal: true });
+  const modelSpecs = req.config?.modelSpecs?.list;
+  /** @type {TModelSpec | null} */
+  let modelSpec = null;
+  if (spec != null && spec !== '') {
+    modelSpec = modelSpecs?.find((s) => s.name === spec) || null;
+  }
   /** @type {TEphemeralAgent | null} */
   const ephemeralAgent = req.body.ephemeralAgent;
   const mcpServers = new Set(ephemeralAgent?.mcp);
+  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);
   }
 
+  const addedServers = new Set();
   if (mcpServers.size > 0) {
-    for (const toolName of Object.keys(availableTools)) {
-      if (!toolName.includes(mcp_delimiter)) {
+    for (const mcpServer of mcpServers) {
+      if (addedServers.has(mcpServer)) {
         continue;
       }
-      const mcpServer = toolName.split(mcp_delimiter)?.[1];
-      if (mcpServer && mcpServers.has(mcpServer)) {
-        tools.push(toolName);
+      const serverTools = await getMCPServerTools(userId, mcpServer);
+      if (!serverTools) {
+        tools.push(`${mcp_all}${mcp_delimiter}${mcpServer}`);
+        addedServers.add(mcpServer);
+        continue;
       }
+      tools.push(...Object.keys(serverTools));
+      addedServers.add(mcpServer);
     }
   }
 
   const instructions = req.body.promptPrefix;
-  return {
+  const result = {
     id: agent_id,
     instructions,
     provider: endpoint,
@@ -98,6 +123,11 @@ const loadEphemeralAgent = async ({ req, agent_id, endpoint, model_parameters: _
     model,
     tools,
   };
+
+  if (ephemeralAgent?.artifacts != null && ephemeralAgent.artifacts) {
+    result.artifacts = ephemeralAgent.artifacts;
+  }
+  return result;
 };
 
 /**
@@ -105,17 +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,
@@ -126,29 +157,7 @@ const loadAgent = async ({ req, agent_id, endpoint, model_parameters }) => {
   }
 
   agent.version = agent.versions ? agent.versions.length : 0;
-
-  if (agent.author.toString() === req.user.id) {
-    return agent;
-  }
-
-  if (!agent.projectIds) {
-    return null;
-  }
-
-  const cache = getLogStores(CONFIG_STORE);
-  /** @type {TStartupConfig} */
-  const cachedStartupConfig = await cache.get(STARTUP_CONFIG);
-  let { instanceProjectId } = cachedStartupConfig ?? {};
-  if (!instanceProjectId) {
-    instanceProjectId = (await getProjectByName(GLOBAL_PROJECT_NAME, '_id'))._id.toString();
-  }
-
-  for (const projectObjectId of agent.projectIds) {
-    const projectId = projectObjectId.toString();
-    if (projectId === instanceProjectId) {
-      return agent;
-    }
-  }
+  return agent;
 };
 
 /**
@@ -178,7 +187,7 @@ const isDuplicateVersion = (updateData, currentData, versions, actionsHash = nul
     'actionsHash', // Exclude actionsHash from direct comparison
   ];
 
-  const { $push, $pull, $addToSet, ...directUpdates } = updateData;
+  const { $push: _$push, $pull: _$pull, $addToSet: _$addToSet, ...directUpdates } = updateData;
 
   if (Object.keys(directUpdates).length === 0 && !actionsHash) {
     return null;
@@ -197,54 +206,116 @@ const isDuplicateVersion = (updateData, currentData, versions, actionsHash = nul
 
   let isMatch = true;
   for (const field of importantFields) {
-    if (!wouldBeVersion[field] && !lastVersion[field]) {
+    const wouldBeValue = wouldBeVersion[field];
+    const lastVersionValue = lastVersion[field];
+
+    // Skip if both are undefined/null
+    if (!wouldBeValue && !lastVersionValue) {
       continue;
     }
 
-    if (Array.isArray(wouldBeVersion[field]) && Array.isArray(lastVersion[field])) {
-      if (wouldBeVersion[field].length !== lastVersion[field].length) {
+    // Handle arrays
+    if (Array.isArray(wouldBeValue) || Array.isArray(lastVersionValue)) {
+      // Normalize: treat undefined/null as empty array for comparison
+      let wouldBeArr;
+      if (Array.isArray(wouldBeValue)) {
+        wouldBeArr = wouldBeValue;
+      } else if (wouldBeValue == null) {
+        wouldBeArr = [];
+      } else {
+        wouldBeArr = [wouldBeValue];
+      }
+
+      let lastVersionArr;
+      if (Array.isArray(lastVersionValue)) {
+        lastVersionArr = lastVersionValue;
+      } else if (lastVersionValue == null) {
+        lastVersionArr = [];
+      } else {
+        lastVersionArr = [lastVersionValue];
+      }
+
+      if (wouldBeArr.length !== lastVersionArr.length) {
         isMatch = false;
         break;
       }
 
       // Special handling for projectIds (MongoDB ObjectIds)
       if (field === 'projectIds') {
-        const wouldBeIds = wouldBeVersion[field].map((id) => id.toString()).sort();
-        const versionIds = lastVersion[field].map((id) => id.toString()).sort();
+        const wouldBeIds = wouldBeArr.map((id) => id.toString()).sort();
+        const versionIds = lastVersionArr.map((id) => id.toString()).sort();
 
         if (!wouldBeIds.every((id, i) => id === versionIds[i])) {
           isMatch = false;
           break;
         }
       }
-      // Handle arrays of objects like tool_kwargs
-      else if (typeof wouldBeVersion[field][0] === 'object' && wouldBeVersion[field][0] !== null) {
-        const sortedWouldBe = [...wouldBeVersion[field]].map((item) => JSON.stringify(item)).sort();
-        const sortedVersion = [...lastVersion[field]].map((item) => JSON.stringify(item)).sort();
+      // Handle arrays of objects
+      else if (
+        wouldBeArr.length > 0 &&
+        typeof wouldBeArr[0] === 'object' &&
+        wouldBeArr[0] !== null
+      ) {
+        const sortedWouldBe = [...wouldBeArr].map((item) => JSON.stringify(item)).sort();
+        const sortedVersion = [...lastVersionArr].map((item) => JSON.stringify(item)).sort();
 
         if (!sortedWouldBe.every((item, i) => item === sortedVersion[i])) {
           isMatch = false;
           break;
         }
       } else {
-        const sortedWouldBe = [...wouldBeVersion[field]].sort();
-        const sortedVersion = [...lastVersion[field]].sort();
+        const sortedWouldBe = [...wouldBeArr].sort();
+        const sortedVersion = [...lastVersionArr].sort();
 
         if (!sortedWouldBe.every((item, i) => item === sortedVersion[i])) {
           isMatch = false;
           break;
         }
       }
-    } else if (field === 'model_parameters') {
-      const wouldBeParams = wouldBeVersion[field] || {};
-      const lastVersionParams = lastVersion[field] || {};
-      if (JSON.stringify(wouldBeParams) !== JSON.stringify(lastVersionParams)) {
+    }
+    // Handle objects
+    else if (typeof wouldBeValue === 'object' && wouldBeValue !== null) {
+      const lastVersionObj =
+        typeof lastVersionValue === 'object' && lastVersionValue !== null ? lastVersionValue : {};
+
+      // For empty objects, normalize the comparison
+      const wouldBeKeys = Object.keys(wouldBeValue);
+      const lastVersionKeys = Object.keys(lastVersionObj);
+
+      // If both are empty objects, they're equal
+      if (wouldBeKeys.length === 0 && lastVersionKeys.length === 0) {
+        continue;
+      }
+
+      // Otherwise do a deep comparison
+      if (JSON.stringify(wouldBeValue) !== JSON.stringify(lastVersionObj)) {
+        isMatch = false;
+        break;
+      }
+    }
+    // Handle primitive values
+    else {
+      // For primitives, handle the case where one is undefined and the other is a default value
+      if (wouldBeValue !== lastVersionValue) {
+        // Special handling for boolean false vs undefined
+        if (
+          typeof wouldBeValue === 'boolean' &&
+          wouldBeValue === false &&
+          lastVersionValue === undefined
+        ) {
+          continue;
+        }
+        // Special handling for empty string vs undefined
+        if (
+          typeof wouldBeValue === 'string' &&
+          wouldBeValue === '' &&
+          lastVersionValue === undefined
+        ) {
+          continue;
+        }
         isMatch = false;
         break;
       }
-    } else if (wouldBeVersion[field] !== lastVersion[field]) {
-      isMatch = false;
-      break;
     }
   }
 
@@ -273,7 +344,14 @@ const updateAgent = async (searchParameter, updateData, options = {}) => {
 
   const currentAgent = await Agent.findOne(searchParameter);
   if (currentAgent) {
-    const { __v, _id, id, versions, author, ...versionData } = currentAgent.toObject();
+    const {
+      __v,
+      _id,
+      id: __id,
+      versions,
+      author: _author,
+      ...versionData
+    } = currentAgent.toObject();
     const { $push, $pull, $addToSet, ...directUpdates } = updateData;
 
     let actionsHash = null;
@@ -311,17 +389,10 @@ const updateAgent = async (searchParameter, updateData, options = {}) => {
     if (shouldCreateVersion) {
       const duplicateVersion = isDuplicateVersion(updateData, versionData, versions, actionsHash);
       if (duplicateVersion && !forceVersion) {
-        const error = new Error(
-          'Duplicate version: This would create a version identical to an existing one',
-        );
-        error.statusCode = 409;
-        error.details = {
-          duplicateVersion,
-          versionIndex: versions.findIndex(
-            (v) => JSON.stringify(duplicateVersion) === JSON.stringify(v),
-          ),
-        };
-        throw error;
+        // No changes detected, return the current agent without creating a new version
+        const agentObj = currentAgent.toObject();
+        agentObj.version = versions.length;
+        return agentObj;
       }
     }
 
@@ -460,12 +531,117 @@ const deleteAgent = async (searchParameter) => {
   const agent = await Agent.findOneAndDelete(searchParameter);
   if (agent) {
     await removeAgentFromAllProjects(agent.id);
+    await removeAllPermissions({
+      resourceType: ResourceType.AGENT,
+      resourceId: agent._id,
+    });
   }
   return agent;
 };
 
+/**
+ * Get agents by accessible IDs with optional cursor-based pagination.
+ * @param {Object} params - The parameters for getting accessible agents.
+ * @param {Array} [params.accessibleIds] - Array of agent ObjectIds the user has ACL access to.
+ * @param {Object} [params.otherParams] - Additional query parameters (including author filter).
+ * @param {number} [params.limit] - Number of agents to return (max 100). If not provided, returns all agents.
+ * @param {string} [params.after] - Cursor for pagination - get agents after this cursor. // base64 encoded JSON string with updatedAt and _id.
+ * @returns {Promise<Object>} A promise that resolves to an object containing the agents data and pagination info.
+ */
+const getListAgentsByAccess = async ({
+  accessibleIds = [],
+  otherParams = {},
+  limit = null,
+  after = null,
+}) => {
+  const isPaginated = limit !== null && limit !== undefined;
+  const normalizedLimit = isPaginated ? Math.min(Math.max(1, parseInt(limit) || 20), 100) : null;
+
+  // Build base query combining ACL accessible agents with other filters
+  const baseQuery = { ...otherParams, _id: { $in: accessibleIds } };
+
+  // Add cursor condition
+  if (after) {
+    try {
+      const cursor = JSON.parse(Buffer.from(after, 'base64').toString('utf8'));
+      const { updatedAt, _id } = cursor;
+
+      const cursorCondition = {
+        $or: [
+          { updatedAt: { $lt: new Date(updatedAt) } },
+          { updatedAt: new Date(updatedAt), _id: { $gt: new mongoose.Types.ObjectId(_id) } },
+        ],
+      };
+
+      // Merge cursor condition with base query
+      if (Object.keys(baseQuery).length > 0) {
+        baseQuery.$and = [{ ...baseQuery }, cursorCondition];
+        // Remove the original conditions from baseQuery to avoid duplication
+        Object.keys(baseQuery).forEach((key) => {
+          if (key !== '$and') delete baseQuery[key];
+        });
+      } else {
+        Object.assign(baseQuery, cursorCondition);
+      }
+    } catch (error) {
+      logger.warn('Invalid cursor:', error.message);
+    }
+  }
+
+  let query = Agent.find(baseQuery, {
+    id: 1,
+    _id: 1,
+    name: 1,
+    avatar: 1,
+    author: 1,
+    projectIds: 1,
+    description: 1,
+    updatedAt: 1,
+    category: 1,
+    support_contact: 1,
+    is_promoted: 1,
+  }).sort({ updatedAt: -1, _id: 1 });
+
+  // Only apply limit if pagination is requested
+  if (isPaginated) {
+    query = query.limit(normalizedLimit + 1);
+  }
+
+  const agents = await query.lean();
+
+  const hasMore = isPaginated ? agents.length > normalizedLimit : false;
+  const data = (isPaginated ? agents.slice(0, normalizedLimit) : agents).map((agent) => {
+    if (agent.author) {
+      agent.author = agent.author.toString();
+    }
+    return agent;
+  });
+
+  // Generate next cursor only if paginated
+  let nextCursor = null;
+  if (isPaginated && hasMore && data.length > 0) {
+    const lastAgent = agents[normalizedLimit - 1];
+    nextCursor = Buffer.from(
+      JSON.stringify({
+        updatedAt: lastAgent.updatedAt.toISOString(),
+        _id: lastAgent._id.toString(),
+      }),
+    ).toString('base64');
+  }
+
+  return {
+    object: 'list',
+    data,
+    first_id: data.length > 0 ? data[0].id : null,
+    last_id: data.length > 0 ? data[data.length - 1].id : null,
+    has_more: hasMore,
+    after: nextCursor,
+  };
+};
+
 /**
  * Get all agents.
+ * @deprecated Use getListAgentsByAccess for ACL-aware agent listing
  * @param {Object} searchParameter - The search parameters to find matching agents.
  * @param {string} searchParameter.author - The user ID of the agent's author.
  * @returns {Promise<Object>} A promise that resolves to an object containing the agents data and pagination info.
@@ -484,13 +660,15 @@ const getListAgents = async (searchParameter) => {
   const agents = (
     await Agent.find(query, {
       id: 1,
-      _id: 0,
+      _id: 1,
       name: 1,
       avatar: 1,
       author: 1,
       projectIds: 1,
       description: 1,
+      // @deprecated - isCollaborative replaced by ACL permissions
       isCollaborative: 1,
+      category: 1,
     }).lean()
   ).map((agent) => {
     if (agent.author?.toString() !== author) {
@@ -519,7 +697,7 @@ const getListAgents = async (searchParameter) => {
  * This function also updates the corresponding projects to include or exclude the agent ID.
  *
  * @param {Object} params - Parameters for updating the agent's projects.
- * @param {MongoUser} params.user - Parameters for updating the agent's projects.
+ * @param {IUser} params.user - Parameters for updating the agent's projects.
  * @param {string} params.agentId - The ID of the agent to update.
  * @param {string[]} [params.projectIds] - Array of project IDs to add to the agent.
  * @param {string[]} [params.removeProjectIds] - Array of project IDs to remove from the agent.
@@ -656,6 +834,14 @@ const generateActionMetadataHash = async (actionIds, actions) => {
 
   return hashHex;
 };
+/**
+ * Counts the number of promoted agents.
+ * @returns  {Promise<number>} - The count of promoted agents
+ */
+const countPromotedAgents = async () => {
+  const count = await Agent.countDocuments({ is_promoted: true });
+  return count;
+};
 
 /**
  * Load a default agent based on the endpoint
@@ -665,6 +851,7 @@ const generateActionMetadataHash = async (actionIds, actions) => {
 
 module.exports = {
   getAgent,
+  getAgents,
   loadAgent,
   createAgent,
   updateAgent,
@@ -673,6 +860,8 @@ module.exports = {
   revertAgentVersion,
   updateAgentProjects,
   addAgentResourceFile,
+  getListAgentsByAccess,
   removeAgentResourceFiles,
   generateActionMetadataHash,
+  countPromotedAgents,
 };

api/models/Agent.spec.js

@@ -8,12 +8,14 @@ process.env.CREDS_IV = '0123456789abcdef';
 
 jest.mock('~/server/services/Config', () => ({
   getCachedTools: jest.fn(),
+  getMCPServerTools: jest.fn(),
 }));
 
 const mongoose = require('mongoose');
 const { v4: uuidv4 } = require('uuid');
 const { agentSchema } = require('@librechat/data-schemas');
 const { MongoMemoryServer } = require('mongodb-memory-server');
+const { AccessRoleIds, ResourceType, PrincipalType } = require('librechat-data-provider');
 const {
   getAgent,
   loadAgent,
@@ -21,13 +23,16 @@ const {
   updateAgent,
   deleteAgent,
   getListAgents,
+  getListAgentsByAccess,
+  revertAgentVersion,
   updateAgentProjects,
   addAgentResourceFile,
   removeAgentResourceFiles,
   generateActionMetadataHash,
-  revertAgentVersion,
 } = require('./Agent');
-const { getCachedTools } = require('~/server/services/Config');
+const permissionService = require('~/server/services/PermissionService');
+const { getCachedTools, getMCPServerTools } = require('~/server/services/Config');
+const { AclEntry } = require('~/db/models');
 
 /**
  * @type {import('mongoose').Model<import('@librechat/data-schemas').IAgent>}
@@ -407,12 +412,26 @@ describe('models/Agent', () => {
 
   describe('Agent CRUD Operations', () => {
     let mongoServer;
+    let AccessRole;
 
     beforeAll(async () => {
       mongoServer = await MongoMemoryServer.create();
       const mongoUri = mongoServer.getUri();
       Agent = mongoose.models.Agent || mongoose.model('Agent', agentSchema);
       await mongoose.connect(mongoUri);
+
+      // Initialize models
+      const dbModels = require('~/db/models');
+      AccessRole = dbModels.AccessRole;
+
+      // Create necessary access roles for agents
+      await AccessRole.create({
+        accessRoleId: AccessRoleIds.AGENT_OWNER,
+        name: 'Owner',
+        description: 'Full control over agents',
+        resourceType: ResourceType.AGENT,
+        permBits: 15, // VIEW | EDIT | DELETE | SHARE
+      });
     }, 20000);
 
     afterAll(async () => {
@@ -468,6 +487,51 @@ describe('models/Agent', () => {
       expect(agentAfterDelete).toBeNull();
     });
 
+    test('should remove ACL entries when deleting an agent', async () => {
+      const agentId = `agent_${uuidv4()}`;
+      const authorId = new mongoose.Types.ObjectId();
+
+      // Create agent
+      const agent = await createAgent({
+        id: agentId,
+        name: 'Agent With Permissions',
+        provider: 'test',
+        model: 'test-model',
+        author: authorId,
+      });
+
+      // Grant permissions (simulating sharing)
+      await permissionService.grantPermission({
+        principalType: PrincipalType.USER,
+        principalId: authorId,
+        resourceType: ResourceType.AGENT,
+        resourceId: agent._id,
+        accessRoleId: AccessRoleIds.AGENT_OWNER,
+        grantedBy: authorId,
+      });
+
+      // Verify ACL entry exists
+      const aclEntriesBefore = await AclEntry.find({
+        resourceType: ResourceType.AGENT,
+        resourceId: agent._id,
+      });
+      expect(aclEntriesBefore).toHaveLength(1);
+
+      // Delete the agent
+      await deleteAgent({ id: agentId });
+
+      // Verify agent is deleted
+      const agentAfterDelete = await getAgent({ id: agentId });
+      expect(agentAfterDelete).toBeNull();
+
+      // Verify ACL entries are removed
+      const aclEntriesAfter = await AclEntry.find({
+        resourceType: ResourceType.AGENT,
+        resourceId: agent._id,
+      });
+      expect(aclEntriesAfter).toHaveLength(0);
+    });
+
     test('should list agents by author', async () => {
       const authorId = new mongoose.Types.ObjectId();
       const otherAuthorId = new mongoose.Types.ObjectId();
@@ -879,45 +943,31 @@ describe('models/Agent', () => {
       expect(emptyParamsAgent.model_parameters).toEqual({});
     });
 
-    test('should detect duplicate versions and reject updates', async () => {
-      const originalConsoleError = console.error;
-      console.error = jest.fn();
+    test('should not create new version for duplicate updates', async () => {
+      const authorId = new mongoose.Types.ObjectId();
+      const testCases = generateVersionTestCases();
 
-      try {
-        const authorId = new mongoose.Types.ObjectId();
-        const testCases = generateVersionTestCases();
+      for (const testCase of testCases) {
+        const testAgentId = `agent_${uuidv4()}`;
 
-        for (const testCase of testCases) {
-          const testAgentId = `agent_${uuidv4()}`;
+        await createAgent({
+          id: testAgentId,
+          provider: 'test',
+          model: 'test-model',
+          author: authorId,
+          ...testCase.initial,
+        });
 
-          await createAgent({
-            id: testAgentId,
-            provider: 'test',
-            model: 'test-model',
-            author: authorId,
-            ...testCase.initial,
-          });
+        const updatedAgent = await updateAgent({ id: testAgentId }, testCase.update);
+        expect(updatedAgent.versions).toHaveLength(2); // No new version created
 
-          await updateAgent({ id: testAgentId }, testCase.update);
+        // Update with duplicate data should succeed but not create a new version
+        const duplicateUpdate = await updateAgent({ id: testAgentId }, testCase.duplicate);
 
-          let error;
-          try {
-            await updateAgent({ id: testAgentId }, testCase.duplicate);
-          } catch (e) {
-            error = e;
-          }
+        expect(duplicateUpdate.versions).toHaveLength(2); // No new version created
 
-          expect(error).toBeDefined();
-          expect(error.message).toContain('Duplicate version');
-          expect(error.statusCode).toBe(409);
-          expect(error.details).toBeDefined();
-          expect(error.details.duplicateVersion).toBeDefined();
-
-          const agent = await getAgent({ id: testAgentId });
-          expect(agent.versions).toHaveLength(2);
-        }
-      } finally {
-        console.error = originalConsoleError;
+        const agent = await getAgent({ id: testAgentId });
+        expect(agent.versions).toHaveLength(2);
       }
     });
 
@@ -1093,20 +1143,13 @@ describe('models/Agent', () => {
       expect(secondUpdate.versions).toHaveLength(3);
 
       // Update without forceVersion and no changes should not create a version
-      let error;
-      try {
-        await updateAgent(
-          { id: agentId },
-          { tools: ['listEvents_action_test.com', 'createEvent_action_test.com'] },
-          { updatingUserId: authorId.toString(), forceVersion: false },
-        );
-      } catch (e) {
-        error = e;
-      }
+      const duplicateUpdate = await updateAgent(
+        { id: agentId },
+        { tools: ['listEvents_action_test.com', 'createEvent_action_test.com'] },
+        { updatingUserId: authorId.toString(), forceVersion: false },
+      );
 
-      expect(error).toBeDefined();
-      expect(error.message).toContain('Duplicate version');
-      expect(error.statusCode).toBe(409);
+      expect(duplicateUpdate.versions).toHaveLength(3); // No new version created
     });
 
     test('should handle isDuplicateVersion with arrays containing null/undefined values', async () => {
@@ -1258,6 +1301,335 @@ describe('models/Agent', () => {
       expect(secondUpdate.versions).toHaveLength(3);
     });
 
+    test('should detect changes in support_contact fields', async () => {
+      const agentId = `agent_${uuidv4()}`;
+      const authorId = new mongoose.Types.ObjectId();
+
+      // Create agent with initial support_contact
+      await createAgent({
+        id: agentId,
+        name: 'Agent with Support Contact',
+        provider: 'test',
+        model: 'test-model',
+        author: authorId,
+        support_contact: {
+          name: 'Initial Support',
+          email: 'initial@support.com',
+        },
+      });
+
+      // Update support_contact name only
+      const firstUpdate = await updateAgent(
+        { id: agentId },
+        {
+          support_contact: {
+            name: 'Updated Support',
+            email: 'initial@support.com',
+          },
+        },
+      );
+
+      expect(firstUpdate.versions).toHaveLength(2);
+      expect(firstUpdate.support_contact.name).toBe('Updated Support');
+      expect(firstUpdate.support_contact.email).toBe('initial@support.com');
+
+      // Update support_contact email only
+      const secondUpdate = await updateAgent(
+        { id: agentId },
+        {
+          support_contact: {
+            name: 'Updated Support',
+            email: 'updated@support.com',
+          },
+        },
+      );
+
+      expect(secondUpdate.versions).toHaveLength(3);
+      expect(secondUpdate.support_contact.email).toBe('updated@support.com');
+
+      // Try to update with same support_contact - should be detected as duplicate but return successfully
+      const duplicateUpdate = await updateAgent(
+        { id: agentId },
+        {
+          support_contact: {
+            name: 'Updated Support',
+            email: 'updated@support.com',
+          },
+        },
+      );
+
+      // Should not create a new version
+      expect(duplicateUpdate.versions).toHaveLength(3);
+      expect(duplicateUpdate.version).toBe(3);
+      expect(duplicateUpdate.support_contact.email).toBe('updated@support.com');
+    });
+
+    test('should handle support_contact from empty to populated', async () => {
+      const agentId = `agent_${uuidv4()}`;
+      const authorId = new mongoose.Types.ObjectId();
+
+      // Create agent without support_contact
+      const agent = await createAgent({
+        id: agentId,
+        name: 'Agent without Support',
+        provider: 'test',
+        model: 'test-model',
+        author: authorId,
+      });
+
+      // Verify support_contact is undefined since it wasn't provided
+      expect(agent.support_contact).toBeUndefined();
+
+      // Update to add support_contact
+      const updated = await updateAgent(
+        { id: agentId },
+        {
+          support_contact: {
+            name: 'New Support Team',
+            email: 'support@example.com',
+          },
+        },
+      );
+
+      expect(updated.versions).toHaveLength(2);
+      expect(updated.support_contact.name).toBe('New Support Team');
+      expect(updated.support_contact.email).toBe('support@example.com');
+    });
+
+    test('should handle support_contact edge cases in isDuplicateVersion', async () => {
+      const agentId = `agent_${uuidv4()}`;
+      const authorId = new mongoose.Types.ObjectId();
+
+      // Create agent with support_contact
+      await createAgent({
+        id: agentId,
+        name: 'Edge Case Agent',
+        provider: 'test',
+        model: 'test-model',
+        author: authorId,
+        support_contact: {
+          name: 'Support',
+          email: 'support@test.com',
+        },
+      });
+
+      // Update to empty support_contact
+      const emptyUpdate = await updateAgent(
+        { id: agentId },
+        {
+          support_contact: {},
+        },
+      );
+
+      expect(emptyUpdate.versions).toHaveLength(2);
+      expect(emptyUpdate.support_contact).toEqual({});
+
+      // Update back to populated support_contact
+      const repopulated = await updateAgent(
+        { id: agentId },
+        {
+          support_contact: {
+            name: 'Support',
+            email: 'support@test.com',
+          },
+        },
+      );
+
+      expect(repopulated.versions).toHaveLength(3);
+
+      // Verify all versions have correct support_contact
+      const finalAgent = await getAgent({ id: agentId });
+      expect(finalAgent.versions[0].support_contact).toEqual({
+        name: 'Support',
+        email: 'support@test.com',
+      });
+      expect(finalAgent.versions[1].support_contact).toEqual({});
+      expect(finalAgent.versions[2].support_contact).toEqual({
+        name: 'Support',
+        email: 'support@test.com',
+      });
+    });
+
+    test('should preserve support_contact in version history', async () => {
+      const agentId = `agent_${uuidv4()}`;
+      const authorId = new mongoose.Types.ObjectId();
+
+      // Create agent
+      await createAgent({
+        id: agentId,
+        name: 'Version History Test',
+        provider: 'test',
+        model: 'test-model',
+        author: authorId,
+        support_contact: {
+          name: 'Initial Contact',
+          email: 'initial@test.com',
+        },
+      });
+
+      // Multiple updates with different support_contact values
+      await updateAgent(
+        { id: agentId },
+        {
+          support_contact: {
+            name: 'Second Contact',
+            email: 'second@test.com',
+          },
+        },
+      );
+
+      await updateAgent(
+        { id: agentId },
+        {
+          support_contact: {
+            name: 'Third Contact',
+            email: 'third@test.com',
+          },
+        },
+      );
+
+      const finalAgent = await getAgent({ id: agentId });
+
+      // Verify version history
+      expect(finalAgent.versions).toHaveLength(3);
+      expect(finalAgent.versions[0].support_contact).toEqual({
+        name: 'Initial Contact',
+        email: 'initial@test.com',
+      });
+      expect(finalAgent.versions[1].support_contact).toEqual({
+        name: 'Second Contact',
+        email: 'second@test.com',
+      });
+      expect(finalAgent.versions[2].support_contact).toEqual({
+        name: 'Third Contact',
+        email: 'third@test.com',
+      });
+
+      // Current state should match last version
+      expect(finalAgent.support_contact).toEqual({
+        name: 'Third Contact',
+        email: 'third@test.com',
+      });
+    });
+
+    test('should handle partial support_contact updates', async () => {
+      const agentId = `agent_${uuidv4()}`;
+      const authorId = new mongoose.Types.ObjectId();
+
+      // Create agent with full support_contact
+      await createAgent({
+        id: agentId,
+        name: 'Partial Update Test',
+        provider: 'test',
+        model: 'test-model',
+        author: authorId,
+        support_contact: {
+          name: 'Original Name',
+          email: 'original@email.com',
+        },
+      });
+
+      // MongoDB's findOneAndUpdate will replace the entire support_contact object
+      // So we need to verify that partial updates still work correctly
+      const updated = await updateAgent(
+        { id: agentId },
+        {
+          support_contact: {
+            name: 'New Name',
+            email: '', // Empty email
+          },
+        },
+      );
+
+      expect(updated.versions).toHaveLength(2);
+      expect(updated.support_contact.name).toBe('New Name');
+      expect(updated.support_contact.email).toBe('');
+
+      // Verify isDuplicateVersion works with partial changes - should return successfully without creating new version
+      const duplicateUpdate = await updateAgent(
+        { id: agentId },
+        {
+          support_contact: {
+            name: 'New Name',
+            email: '',
+          },
+        },
+      );
+
+      // Should not create a new version since content is the same
+      expect(duplicateUpdate.versions).toHaveLength(2);
+      expect(duplicateUpdate.version).toBe(2);
+      expect(duplicateUpdate.support_contact.name).toBe('New Name');
+      expect(duplicateUpdate.support_contact.email).toBe('');
+    });
+
+    // Edge Cases
+    describe.each([
+      {
+        operation: 'add',
+        name: 'empty file_id',
+        needsAgent: true,
+        params: { tool_resource: 'file_search', file_id: '' },
+        shouldResolve: true,
+      },
+      {
+        operation: 'add',
+        name: 'non-existent agent',
+        needsAgent: false,
+        params: { tool_resource: 'file_search', file_id: 'file123' },
+        shouldResolve: false,
+        error: 'Agent not found for adding resource file',
+      },
+    ])('addAgentResourceFile with $name', ({ needsAgent, params, shouldResolve, error }) => {
+      test(`should ${shouldResolve ? 'resolve' : 'reject'}`, async () => {
+        const agent = needsAgent ? await createBasicAgent() : null;
+        const agent_id = needsAgent ? agent.id : `agent_${uuidv4()}`;
+
+        if (shouldResolve) {
+          await expect(addAgentResourceFile({ agent_id, ...params })).resolves.toBeDefined();
+        } else {
+          await expect(addAgentResourceFile({ agent_id, ...params })).rejects.toThrow(error);
+        }
+      });
+    });
+
+    describe.each([
+      {
+        name: 'empty files array',
+        files: [],
+        needsAgent: true,
+        shouldResolve: true,
+      },
+      {
+        name: 'non-existent tool_resource',
+        files: [{ tool_resource: 'non_existent_tool', file_id: 'file123' }],
+        needsAgent: true,
+        shouldResolve: true,
+      },
+      {
+        name: 'non-existent agent',
+        files: [{ tool_resource: 'file_search', file_id: 'file123' }],
+        needsAgent: false,
+        shouldResolve: false,
+        error: 'Agent not found for removing resource files',
+      },
+    ])('removeAgentResourceFiles with $name', ({ files, needsAgent, shouldResolve, error }) => {
+      test(`should ${shouldResolve ? 'resolve' : 'reject'}`, async () => {
+        const agent = needsAgent ? await createBasicAgent() : null;
+        const agent_id = needsAgent ? agent.id : `agent_${uuidv4()}`;
+
+        if (shouldResolve) {
+          const result = await removeAgentResourceFiles({ agent_id, files });
+          expect(result).toBeDefined();
+          if (agent) {
+            expect(result.id).toBe(agent.id);
+          }
+        } else {
+          await expect(removeAgentResourceFiles({ agent_id, files })).rejects.toThrow(error);
+        }
+      });
+    });
+
     describe('Edge Cases', () => {
       test('should handle extremely large version history', async () => {
         const agentId = `agent_${uuidv4()}`;
@@ -1558,6 +1930,16 @@ describe('models/Agent', () => {
         another_tool: {},
       });
 
+      // Mock getMCPServerTools to return tools for each server
+      getMCPServerTools.mockImplementation(async (_userId, server) => {
+        if (server === 'server1') {
+          return { tool1_mcp_server1: {} };
+        } else if (server === 'server2') {
+          return { tool2_mcp_server2: {} };
+        }
+        return null;
+      });
+
       const mockReq = {
         user: { id: 'user123' },
         body: {
@@ -1633,7 +2015,7 @@ describe('models/Agent', () => {
       expect(result.version).toBe(1);
     });
 
-    test('should return null when user is not author and agent has no projectIds', async () => {
+    test('should return agent even when user is not author (permissions checked at route level)', async () => {
       const authorId = new mongoose.Types.ObjectId();
       const userId = new mongoose.Types.ObjectId();
       const agentId = `agent_${uuidv4()}`;
@@ -1654,7 +2036,11 @@ describe('models/Agent', () => {
         model_parameters: { model: 'gpt-4' },
       });
 
-      expect(result).toBeFalsy();
+      // With the new permission system, loadAgent returns the agent regardless of permissions
+      // Permission checks are handled at the route level via middleware
+      expect(result).toBeTruthy();
+      expect(result.id).toBe(agentId);
+      expect(result.name).toBe('Test Agent');
     });
 
     test('should handle ephemeral agent with no MCP servers', async () => {
@@ -1738,6 +2124,14 @@ describe('models/Agent', () => {
 
         getCachedTools.mockResolvedValue(availableTools);
 
+        // Mock getMCPServerTools to return all tools for server1
+        getMCPServerTools.mockImplementation(async (_userId, server) => {
+          if (server === 'server1') {
+            return availableTools; // All 100 tools belong to server1
+          }
+          return null;
+        });
+
         const mockReq = {
           user: { id: 'user123' },
           body: {
@@ -1762,7 +2156,7 @@ describe('models/Agent', () => {
         }
       });
 
-      test('should handle loadAgent with agent from different project', async () => {
+      test('should return agent from different project (permissions checked at route level)', async () => {
         const authorId = new mongoose.Types.ObjectId();
         const userId = new mongoose.Types.ObjectId();
         const agentId = `agent_${uuidv4()}`;
@@ -1785,7 +2179,11 @@ describe('models/Agent', () => {
           model_parameters: { model: 'gpt-4' },
         });
 
-        expect(result).toBeFalsy();
+        // With the new permission system, loadAgent returns the agent regardless of permissions
+        // Permission checks are handled at the route level via middleware
+        expect(result).toBeTruthy();
+        expect(result.id).toBe(agentId);
+        expect(result.name).toBe('Project Agent');
       });
     });
   });
@@ -2275,6 +2673,17 @@ describe('models/Agent', () => {
         tool_mcp_server2: {}, // Different server
       });
 
+      // Mock getMCPServerTools to return only tools matching the server
+      getMCPServerTools.mockImplementation(async (_userId, server) => {
+        if (server === 'server1') {
+          // Only return tool that correctly matches server1 format
+          return { tool_mcp_server1: {} };
+        } else if (server === 'server2') {
+          return { tool_mcp_server2: {} };
+        }
+        return null;
+      });
+
       const mockReq = {
         user: { id: 'user123' },
         body: {
@@ -2400,11 +2809,18 @@ describe('models/Agent', () => {
         agent_ids: ['agent1', 'agent2'],
       });
 
-      await updateAgent({ id: agentId }, { agent_ids: ['agent1', 'agent2', 'agent3'] });
+      const updatedAgent = await updateAgent(
+        { id: agentId },
+        { agent_ids: ['agent1', 'agent2', 'agent3'] },
+      );
+      expect(updatedAgent.versions).toHaveLength(2);
 
-      await expect(
-        updateAgent({ id: agentId }, { agent_ids: ['agent1', 'agent2', 'agent3'] }),
-      ).rejects.toThrow('Duplicate version');
+      // Update with same agent_ids should succeed but not create a new version
+      const duplicateUpdate = await updateAgent(
+        { id: agentId },
+        { agent_ids: ['agent1', 'agent2', 'agent3'] },
+      );
+      expect(duplicateUpdate.versions).toHaveLength(2); // No new version created
     });
 
     test('should handle agent_ids field alongside other fields', async () => {
@@ -2543,9 +2959,10 @@ describe('models/Agent', () => {
       expect(updated.versions).toHaveLength(2);
       expect(updated.agent_ids).toEqual([]);
 
-      await expect(updateAgent({ id: agentId }, { agent_ids: [] })).rejects.toThrow(
-        'Duplicate version',
-      );
+      // Update with same empty agent_ids should succeed but not create a new version
+      const duplicateUpdate = await updateAgent({ id: agentId }, { agent_ids: [] });
+      expect(duplicateUpdate.versions).toHaveLength(2); // No new version created
+      expect(duplicateUpdate.agent_ids).toEqual([]);
     });
 
     test('should handle agent without agent_ids field', async () => {
@@ -2570,6 +2987,299 @@ describe('models/Agent', () => {
   });
 });
 
+describe('Support Contact Field', () => {
+  let mongoServer;
+
+  beforeAll(async () => {
+    mongoServer = await MongoMemoryServer.create();
+    const mongoUri = mongoServer.getUri();
+    Agent = mongoose.models.Agent || mongoose.model('Agent', agentSchema);
+    await mongoose.connect(mongoUri);
+  }, 20000);
+
+  afterAll(async () => {
+    await mongoose.disconnect();
+    await mongoServer.stop();
+  });
+
+  beforeEach(async () => {
+    await Agent.deleteMany({});
+  });
+
+  it('should not create subdocument with ObjectId for support_contact', async () => {
+    const userId = new mongoose.Types.ObjectId();
+    const agentData = {
+      id: 'agent_test_support',
+      name: 'Test Agent',
+      provider: 'openai',
+      model: 'gpt-4',
+      author: userId,
+      support_contact: {
+        name: 'Support Team',
+        email: 'support@example.com',
+      },
+    };
+
+    // Create agent
+    const agent = await createAgent(agentData);
+
+    // Verify support_contact is stored correctly
+    expect(agent.support_contact).toBeDefined();
+    expect(agent.support_contact.name).toBe('Support Team');
+    expect(agent.support_contact.email).toBe('support@example.com');
+
+    // Verify no _id field is created in support_contact
+    expect(agent.support_contact._id).toBeUndefined();
+
+    // Fetch from database to double-check
+    const dbAgent = await Agent.findOne({ id: agentData.id });
+    expect(dbAgent.support_contact).toBeDefined();
+    expect(dbAgent.support_contact.name).toBe('Support Team');
+    expect(dbAgent.support_contact.email).toBe('support@example.com');
+    expect(dbAgent.support_contact._id).toBeUndefined();
+  });
+
+  it('should handle empty support_contact correctly', async () => {
+    const userId = new mongoose.Types.ObjectId();
+    const agentData = {
+      id: 'agent_test_empty_support',
+      name: 'Test Agent',
+      provider: 'openai',
+      model: 'gpt-4',
+      author: userId,
+      support_contact: {},
+    };
+
+    const agent = await createAgent(agentData);
+
+    // Verify empty support_contact is stored as empty object
+    expect(agent.support_contact).toEqual({});
+    expect(agent.support_contact._id).toBeUndefined();
+  });
+
+  it('should handle missing support_contact correctly', async () => {
+    const userId = new mongoose.Types.ObjectId();
+    const agentData = {
+      id: 'agent_test_no_support',
+      name: 'Test Agent',
+      provider: 'openai',
+      model: 'gpt-4',
+      author: userId,
+    };
+
+    const agent = await createAgent(agentData);
+
+    // Verify support_contact is undefined when not provided
+    expect(agent.support_contact).toBeUndefined();
+  });
+
+  describe('getListAgentsByAccess - Security Tests', () => {
+    let userA, userB;
+    let agentA1, agentA2, agentA3;
+
+    beforeEach(async () => {
+      Agent = mongoose.models.Agent || mongoose.model('Agent', agentSchema);
+      await Agent.deleteMany({});
+      await AclEntry.deleteMany({});
+
+      // Create two users
+      userA = new mongoose.Types.ObjectId();
+      userB = new mongoose.Types.ObjectId();
+
+      // Create agents for user A
+      agentA1 = await createAgent({
+        id: `agent_${uuidv4().slice(0, 12)}`,
+        name: 'Agent A1',
+        description: 'User A agent 1',
+        provider: 'openai',
+        model: 'gpt-4',
+        author: userA,
+      });
+
+      agentA2 = await createAgent({
+        id: `agent_${uuidv4().slice(0, 12)}`,
+        name: 'Agent A2',
+        description: 'User A agent 2',
+        provider: 'openai',
+        model: 'gpt-4',
+        author: userA,
+      });
+
+      agentA3 = await createAgent({
+        id: `agent_${uuidv4().slice(0, 12)}`,
+        name: 'Agent A3',
+        description: 'User A agent 3',
+        provider: 'openai',
+        model: 'gpt-4',
+        author: userA,
+      });
+    });
+
+    test('should return empty list when user has no accessible agents (empty accessibleIds)', async () => {
+      // User B has no agents and no shared agents
+      const result = await getListAgentsByAccess({
+        accessibleIds: [],
+        otherParams: {},
+      });
+
+      expect(result.data).toHaveLength(0);
+      expect(result.has_more).toBe(false);
+      expect(result.first_id).toBeNull();
+      expect(result.last_id).toBeNull();
+    });
+
+    test('should not return other users agents when accessibleIds is empty', async () => {
+      // User B trying to list agents with empty accessibleIds should not see User A's agents
+      const result = await getListAgentsByAccess({
+        accessibleIds: [],
+        otherParams: { author: userB },
+      });
+
+      expect(result.data).toHaveLength(0);
+      expect(result.has_more).toBe(false);
+    });
+
+    test('should only return agents in accessibleIds list', async () => {
+      // Give User B access to only one of User A's agents
+      const accessibleIds = [agentA1._id];
+
+      const result = await getListAgentsByAccess({
+        accessibleIds,
+        otherParams: {},
+      });
+
+      expect(result.data).toHaveLength(1);
+      expect(result.data[0].id).toBe(agentA1.id);
+      expect(result.data[0].name).toBe('Agent A1');
+    });
+
+    test('should return multiple accessible agents when provided', async () => {
+      // Give User B access to two of User A's agents
+      const accessibleIds = [agentA1._id, agentA3._id];
+
+      const result = await getListAgentsByAccess({
+        accessibleIds,
+        otherParams: {},
+      });
+
+      expect(result.data).toHaveLength(2);
+      const returnedIds = result.data.map((agent) => agent.id);
+      expect(returnedIds).toContain(agentA1.id);
+      expect(returnedIds).toContain(agentA3.id);
+      expect(returnedIds).not.toContain(agentA2.id);
+    });
+
+    test('should respect other query parameters while enforcing accessibleIds', async () => {
+      // Give access to all agents but filter by name
+      const accessibleIds = [agentA1._id, agentA2._id, agentA3._id];
+
+      const result = await getListAgentsByAccess({
+        accessibleIds,
+        otherParams: { name: 'Agent A2' },
+      });
+
+      expect(result.data).toHaveLength(1);
+      expect(result.data[0].id).toBe(agentA2.id);
+    });
+
+    test('should handle pagination correctly with accessibleIds filter', async () => {
+      // Create more agents
+      const moreAgents = [];
+      for (let i = 4; i <= 10; i++) {
+        const agent = await createAgent({
+          id: `agent_${uuidv4().slice(0, 12)}`,
+          name: `Agent A${i}`,
+          description: `User A agent ${i}`,
+          provider: 'openai',
+          model: 'gpt-4',
+          author: userA,
+        });
+        moreAgents.push(agent);
+      }
+
+      // Give access to all agents
+      const allAgentIds = [agentA1, agentA2, agentA3, ...moreAgents].map((a) => a._id);
+
+      // First page
+      const page1 = await getListAgentsByAccess({
+        accessibleIds: allAgentIds,
+        otherParams: {},
+        limit: 5,
+      });
+
+      expect(page1.data).toHaveLength(5);
+      expect(page1.has_more).toBe(true);
+      expect(page1.after).toBeTruthy();
+
+      // Second page
+      const page2 = await getListAgentsByAccess({
+        accessibleIds: allAgentIds,
+        otherParams: {},
+        limit: 5,
+        after: page1.after,
+      });
+
+      expect(page2.data).toHaveLength(5);
+      expect(page2.has_more).toBe(false);
+
+      // Verify no overlap between pages
+      const page1Ids = page1.data.map((a) => a.id);
+      const page2Ids = page2.data.map((a) => a.id);
+      const intersection = page1Ids.filter((id) => page2Ids.includes(id));
+      expect(intersection).toHaveLength(0);
+    });
+
+    test('should return empty list when accessibleIds contains non-existent IDs', async () => {
+      // Try with non-existent agent IDs
+      const fakeIds = [new mongoose.Types.ObjectId(), new mongoose.Types.ObjectId()];
+
+      const result = await getListAgentsByAccess({
+        accessibleIds: fakeIds,
+        otherParams: {},
+      });
+
+      expect(result.data).toHaveLength(0);
+      expect(result.has_more).toBe(false);
+    });
+
+    test('should handle undefined accessibleIds as empty array', async () => {
+      // When accessibleIds is undefined, it should be treated as empty array
+      const result = await getListAgentsByAccess({
+        accessibleIds: undefined,
+        otherParams: {},
+      });
+
+      expect(result.data).toHaveLength(0);
+      expect(result.has_more).toBe(false);
+    });
+
+    test('should combine accessibleIds with author filter correctly', async () => {
+      // Create an agent for User B
+      const agentB1 = await createAgent({
+        id: `agent_${uuidv4().slice(0, 12)}`,
+        name: 'Agent B1',
+        description: 'User B agent 1',
+        provider: 'openai',
+        model: 'gpt-4',
+        author: userB,
+      });
+
+      // Give User B access to one of User A's agents
+      const accessibleIds = [agentA1._id, agentB1._id];
+
+      // Filter by author should further restrict the results
+      const result = await getListAgentsByAccess({
+        accessibleIds,
+        otherParams: { author: userB },
+      });
+
+      expect(result.data).toHaveLength(1);
+      expect(result.data[0].id).toBe(agentB1.id);
+      expect(result.data[0].author).toBe(userB.toString());
+    });
+  });
+});
+
 function createBasicAgent(overrides = {}) {
   const defaults = {
     id: `agent_${uuidv4()}`,

api/models/Categories.js

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

api/models/Conversation.js

@@ -1,6 +1,5 @@
 const { logger } = require('@librechat/data-schemas');
 const { createTempChatExpirationDate } = require('@librechat/api');
-const getCustomConfig = require('~/server/services/Config/loadCustomConfig');
 const { getMessages, deleteMessages } = require('./Message');
 const { Conversation } = require('~/db/models');
 
@@ -102,8 +101,8 @@ module.exports = {
 
       if (req?.body?.isTemporary) {
         try {
-          const customConfig = await getCustomConfig();
-          update.expiredAt = createTempChatExpirationDate(customConfig);
+          const appConfig = req.config;
+          update.expiredAt = createTempChatExpirationDate(appConfig?.interfaceConfig);
         } catch (err) {
           logger.error('Error creating temporary chat expiration date:', err);
           logger.info(`---\`saveConvo\` context: ${metadata?.context}`);
@@ -175,7 +174,7 @@ module.exports = {
 
     if (search) {
       try {
-        const meiliResults = await Conversation.meiliSearch(search);
+        const meiliResults = await Conversation.meiliSearch(search, { filter: `user = "${user}"` });
         const matchingIds = Array.isArray(meiliResults.hits)
           ? meiliResults.hits.map((result) => result.conversationId)
           : [];

api/models/Conversation.spec.js

@@ -0,0 +1,570 @@
+const mongoose = require('mongoose');
+const { v4: uuidv4 } = require('uuid');
+const { EModelEndpoint } = require('librechat-data-provider');
+const { MongoMemoryServer } = require('mongodb-memory-server');
+const {
+  deleteNullOrEmptyConversations,
+  searchConversation,
+  getConvosByCursor,
+  getConvosQueried,
+  getConvoFiles,
+  getConvoTitle,
+  deleteConvos,
+  saveConvo,
+  getConvo,
+} = require('./Conversation');
+jest.mock('~/server/services/Config/app');
+jest.mock('./Message');
+const { getMessages, deleteMessages } = require('./Message');
+
+const { Conversation } = require('~/db/models');
+
+describe('Conversation Operations', () => {
+  let mongoServer;
+  let mockReq;
+  let mockConversationData;
+
+  beforeAll(async () => {
+    mongoServer = await MongoMemoryServer.create();
+    const mongoUri = mongoServer.getUri();
+    await mongoose.connect(mongoUri);
+  });
+
+  afterAll(async () => {
+    await mongoose.disconnect();
+    await mongoServer.stop();
+  });
+
+  beforeEach(async () => {
+    // Clear database
+    await Conversation.deleteMany({});
+
+    // Reset mocks
+    jest.clearAllMocks();
+
+    // Default mock implementations
+    getMessages.mockResolvedValue([]);
+    deleteMessages.mockResolvedValue({ deletedCount: 0 });
+
+    mockReq = {
+      user: { id: 'user123' },
+      body: {},
+      config: {
+        interfaceConfig: {
+          temporaryChatRetention: 24, // Default 24 hours
+        },
+      },
+    };
+
+    mockConversationData = {
+      conversationId: uuidv4(),
+      title: 'Test Conversation',
+      endpoint: EModelEndpoint.openAI,
+    };
+  });
+
+  describe('saveConvo', () => {
+    it('should save a conversation for an authenticated user', async () => {
+      const result = await saveConvo(mockReq, mockConversationData);
+
+      expect(result.conversationId).toBe(mockConversationData.conversationId);
+      expect(result.user).toBe('user123');
+      expect(result.title).toBe('Test Conversation');
+      expect(result.endpoint).toBe(EModelEndpoint.openAI);
+
+      // Verify the conversation was actually saved to the database
+      const savedConvo = await Conversation.findOne({
+        conversationId: mockConversationData.conversationId,
+        user: 'user123',
+      });
+      expect(savedConvo).toBeTruthy();
+      expect(savedConvo.title).toBe('Test Conversation');
+    });
+
+    it('should query messages when saving a conversation', async () => {
+      // Mock messages as ObjectIds
+      const mongoose = require('mongoose');
+      const mockMessages = [new mongoose.Types.ObjectId(), new mongoose.Types.ObjectId()];
+      getMessages.mockResolvedValue(mockMessages);
+
+      await saveConvo(mockReq, mockConversationData);
+
+      // Verify that getMessages was called with correct parameters
+      expect(getMessages).toHaveBeenCalledWith(
+        { conversationId: mockConversationData.conversationId },
+        '_id',
+      );
+    });
+
+    it('should handle newConversationId when provided', async () => {
+      const newConversationId = uuidv4();
+      const result = await saveConvo(mockReq, {
+        ...mockConversationData,
+        newConversationId,
+      });
+
+      expect(result.conversationId).toBe(newConversationId);
+    });
+
+    it('should handle unsetFields metadata', async () => {
+      const metadata = {
+        unsetFields: { someField: 1 },
+      };
+
+      await saveConvo(mockReq, mockConversationData, metadata);
+
+      const savedConvo = await Conversation.findOne({
+        conversationId: mockConversationData.conversationId,
+      });
+      expect(savedConvo.someField).toBeUndefined();
+    });
+  });
+
+  describe('isTemporary conversation handling', () => {
+    it('should save a conversation with expiredAt when isTemporary is true', async () => {
+      // Mock app config with 24 hour retention
+      mockReq.config.interfaceConfig.temporaryChatRetention = 24;
+
+      mockReq.body = { isTemporary: true };
+
+      const beforeSave = new Date();
+      const result = await saveConvo(mockReq, mockConversationData);
+      const afterSave = new Date();
+
+      expect(result.conversationId).toBe(mockConversationData.conversationId);
+      expect(result.expiredAt).toBeDefined();
+      expect(result.expiredAt).toBeInstanceOf(Date);
+
+      // Verify expiredAt is approximately 24 hours in the future
+      const expectedExpirationTime = new Date(beforeSave.getTime() + 24 * 60 * 60 * 1000);
+      const actualExpirationTime = new Date(result.expiredAt);
+
+      expect(actualExpirationTime.getTime()).toBeGreaterThanOrEqual(
+        expectedExpirationTime.getTime() - 1000,
+      );
+      expect(actualExpirationTime.getTime()).toBeLessThanOrEqual(
+        new Date(afterSave.getTime() + 24 * 60 * 60 * 1000 + 1000).getTime(),
+      );
+    });
+
+    it('should save a conversation without expiredAt when isTemporary is false', async () => {
+      mockReq.body = { isTemporary: false };
+
+      const result = await saveConvo(mockReq, mockConversationData);
+
+      expect(result.conversationId).toBe(mockConversationData.conversationId);
+      expect(result.expiredAt).toBeNull();
+    });
+
+    it('should save a conversation without expiredAt when isTemporary is not provided', async () => {
+      // No isTemporary in body
+      mockReq.body = {};
+
+      const result = await saveConvo(mockReq, mockConversationData);
+
+      expect(result.conversationId).toBe(mockConversationData.conversationId);
+      expect(result.expiredAt).toBeNull();
+    });
+
+    it('should use custom retention period from config', async () => {
+      // Mock app config with 48 hour retention
+      mockReq.config.interfaceConfig.temporaryChatRetention = 48;
+
+      mockReq.body = { isTemporary: true };
+
+      const beforeSave = new Date();
+      const result = await saveConvo(mockReq, mockConversationData);
+
+      expect(result.expiredAt).toBeDefined();
+
+      // Verify expiredAt is approximately 48 hours in the future
+      const expectedExpirationTime = new Date(beforeSave.getTime() + 48 * 60 * 60 * 1000);
+      const actualExpirationTime = new Date(result.expiredAt);
+
+      expect(actualExpirationTime.getTime()).toBeGreaterThanOrEqual(
+        expectedExpirationTime.getTime() - 1000,
+      );
+      expect(actualExpirationTime.getTime()).toBeLessThanOrEqual(
+        expectedExpirationTime.getTime() + 1000,
+      );
+    });
+
+    it('should handle minimum retention period (1 hour)', async () => {
+      // Mock app config with less than minimum retention
+      mockReq.config.interfaceConfig.temporaryChatRetention = 0.5; // Half hour - should be clamped to 1 hour
+
+      mockReq.body = { isTemporary: true };
+
+      const beforeSave = new Date();
+      const result = await saveConvo(mockReq, mockConversationData);
+
+      expect(result.expiredAt).toBeDefined();
+
+      // Verify expiredAt is approximately 1 hour in the future (minimum)
+      const expectedExpirationTime = new Date(beforeSave.getTime() + 1 * 60 * 60 * 1000);
+      const actualExpirationTime = new Date(result.expiredAt);
+
+      expect(actualExpirationTime.getTime()).toBeGreaterThanOrEqual(
+        expectedExpirationTime.getTime() - 1000,
+      );
+      expect(actualExpirationTime.getTime()).toBeLessThanOrEqual(
+        expectedExpirationTime.getTime() + 1000,
+      );
+    });
+
+    it('should handle maximum retention period (8760 hours)', async () => {
+      // Mock app config with more than maximum retention
+      mockReq.config.interfaceConfig.temporaryChatRetention = 10000; // Should be clamped to 8760 hours
+
+      mockReq.body = { isTemporary: true };
+
+      const beforeSave = new Date();
+      const result = await saveConvo(mockReq, mockConversationData);
+
+      expect(result.expiredAt).toBeDefined();
+
+      // Verify expiredAt is approximately 8760 hours (1 year) in the future
+      const expectedExpirationTime = new Date(beforeSave.getTime() + 8760 * 60 * 60 * 1000);
+      const actualExpirationTime = new Date(result.expiredAt);
+
+      expect(actualExpirationTime.getTime()).toBeGreaterThanOrEqual(
+        expectedExpirationTime.getTime() - 1000,
+      );
+      expect(actualExpirationTime.getTime()).toBeLessThanOrEqual(
+        expectedExpirationTime.getTime() + 1000,
+      );
+    });
+
+    it('should handle missing config gracefully', async () => {
+      // Simulate missing config - should use default retention period
+      delete mockReq.config;
+
+      mockReq.body = { isTemporary: true };
+
+      const beforeSave = new Date();
+      const result = await saveConvo(mockReq, mockConversationData);
+      const afterSave = new Date();
+
+      // Should still save the conversation with default retention period (30 days)
+      expect(result.conversationId).toBe(mockConversationData.conversationId);
+      expect(result.expiredAt).toBeDefined();
+      expect(result.expiredAt).toBeInstanceOf(Date);
+
+      // Verify expiredAt is approximately 30 days in the future (720 hours)
+      const expectedExpirationTime = new Date(beforeSave.getTime() + 720 * 60 * 60 * 1000);
+      const actualExpirationTime = new Date(result.expiredAt);
+
+      expect(actualExpirationTime.getTime()).toBeGreaterThanOrEqual(
+        expectedExpirationTime.getTime() - 1000,
+      );
+      expect(actualExpirationTime.getTime()).toBeLessThanOrEqual(
+        new Date(afterSave.getTime() + 720 * 60 * 60 * 1000 + 1000).getTime(),
+      );
+    });
+
+    it('should use default retention when config is not provided', async () => {
+      // Mock getAppConfig to return empty config
+      mockReq.config = {}; // Empty config
+
+      mockReq.body = { isTemporary: true };
+
+      const beforeSave = new Date();
+      const result = await saveConvo(mockReq, mockConversationData);
+
+      expect(result.expiredAt).toBeDefined();
+
+      // Default retention is 30 days (720 hours)
+      const expectedExpirationTime = new Date(beforeSave.getTime() + 30 * 24 * 60 * 60 * 1000);
+      const actualExpirationTime = new Date(result.expiredAt);
+
+      expect(actualExpirationTime.getTime()).toBeGreaterThanOrEqual(
+        expectedExpirationTime.getTime() - 1000,
+      );
+      expect(actualExpirationTime.getTime()).toBeLessThanOrEqual(
+        expectedExpirationTime.getTime() + 1000,
+      );
+    });
+
+    it('should update expiredAt when saving existing temporary conversation', async () => {
+      // First save a temporary conversation
+      mockReq.config.interfaceConfig.temporaryChatRetention = 24;
+
+      mockReq.body = { isTemporary: true };
+      const firstSave = await saveConvo(mockReq, mockConversationData);
+      const originalExpiredAt = firstSave.expiredAt;
+
+      // Wait a bit to ensure time difference
+      await new Promise((resolve) => setTimeout(resolve, 100));
+
+      // Save again with same conversationId but different title
+      const updatedData = { ...mockConversationData, title: 'Updated Title' };
+      const secondSave = await saveConvo(mockReq, updatedData);
+
+      // Should update title and create new expiredAt
+      expect(secondSave.title).toBe('Updated Title');
+      expect(secondSave.expiredAt).toBeDefined();
+      expect(new Date(secondSave.expiredAt).getTime()).toBeGreaterThan(
+        new Date(originalExpiredAt).getTime(),
+      );
+    });
+
+    it('should not set expiredAt when updating non-temporary conversation', async () => {
+      // First save a non-temporary conversation
+      mockReq.body = { isTemporary: false };
+      const firstSave = await saveConvo(mockReq, mockConversationData);
+      expect(firstSave.expiredAt).toBeNull();
+
+      // Update without isTemporary flag
+      mockReq.body = {};
+      const updatedData = { ...mockConversationData, title: 'Updated Title' };
+      const secondSave = await saveConvo(mockReq, updatedData);
+
+      expect(secondSave.title).toBe('Updated Title');
+      expect(secondSave.expiredAt).toBeNull();
+    });
+
+    it('should filter out expired conversations in getConvosByCursor', async () => {
+      // Create some test conversations
+      const nonExpiredConvo = await Conversation.create({
+        conversationId: uuidv4(),
+        user: 'user123',
+        title: 'Non-expired',
+        endpoint: EModelEndpoint.openAI,
+        expiredAt: null,
+        updatedAt: new Date(),
+      });
+
+      await Conversation.create({
+        conversationId: uuidv4(),
+        user: 'user123',
+        title: 'Future expired',
+        endpoint: EModelEndpoint.openAI,
+        expiredAt: new Date(Date.now() + 24 * 60 * 60 * 1000), // 24 hours from now
+        updatedAt: new Date(),
+      });
+
+      // Mock Meili search
+      Conversation.meiliSearch = jest.fn().mockResolvedValue({ hits: [] });
+
+      const result = await getConvosByCursor('user123');
+
+      // Should only return conversations with null or non-existent expiredAt
+      expect(result.conversations).toHaveLength(1);
+      expect(result.conversations[0].conversationId).toBe(nonExpiredConvo.conversationId);
+    });
+
+    it('should filter out expired conversations in getConvosQueried', async () => {
+      // Create test conversations
+      const nonExpiredConvo = await Conversation.create({
+        conversationId: uuidv4(),
+        user: 'user123',
+        title: 'Non-expired',
+        endpoint: EModelEndpoint.openAI,
+        expiredAt: null,
+      });
+
+      const expiredConvo = await Conversation.create({
+        conversationId: uuidv4(),
+        user: 'user123',
+        title: 'Expired',
+        endpoint: EModelEndpoint.openAI,
+        expiredAt: new Date(Date.now() + 24 * 60 * 60 * 1000),
+      });
+
+      const convoIds = [
+        { conversationId: nonExpiredConvo.conversationId },
+        { conversationId: expiredConvo.conversationId },
+      ];
+
+      const result = await getConvosQueried('user123', convoIds);
+
+      // Should only return the non-expired conversation
+      expect(result.conversations).toHaveLength(1);
+      expect(result.conversations[0].conversationId).toBe(nonExpiredConvo.conversationId);
+      expect(result.convoMap[nonExpiredConvo.conversationId]).toBeDefined();
+      expect(result.convoMap[expiredConvo.conversationId]).toBeUndefined();
+    });
+  });
+
+  describe('searchConversation', () => {
+    it('should find a conversation by conversationId', async () => {
+      await Conversation.create({
+        conversationId: mockConversationData.conversationId,
+        user: 'user123',
+        title: 'Test',
+        endpoint: EModelEndpoint.openAI,
+      });
+
+      const result = await searchConversation(mockConversationData.conversationId);
+
+      expect(result).toBeTruthy();
+      expect(result.conversationId).toBe(mockConversationData.conversationId);
+      expect(result.user).toBe('user123');
+      expect(result.title).toBeUndefined(); // Only returns conversationId and user
+    });
+
+    it('should return null if conversation not found', async () => {
+      const result = await searchConversation('non-existent-id');
+      expect(result).toBeNull();
+    });
+  });
+
+  describe('getConvo', () => {
+    it('should retrieve a conversation for a user', async () => {
+      await Conversation.create({
+        conversationId: mockConversationData.conversationId,
+        user: 'user123',
+        title: 'Test Conversation',
+        endpoint: EModelEndpoint.openAI,
+      });
+
+      const result = await getConvo('user123', mockConversationData.conversationId);
+
+      expect(result.conversationId).toBe(mockConversationData.conversationId);
+      expect(result.user).toBe('user123');
+      expect(result.title).toBe('Test Conversation');
+    });
+
+    it('should return null if conversation not found', async () => {
+      const result = await getConvo('user123', 'non-existent-id');
+      expect(result).toBeNull();
+    });
+  });
+
+  describe('getConvoTitle', () => {
+    it('should return the conversation title', async () => {
+      await Conversation.create({
+        conversationId: mockConversationData.conversationId,
+        user: 'user123',
+        title: 'Test Title',
+        endpoint: EModelEndpoint.openAI,
+      });
+
+      const result = await getConvoTitle('user123', mockConversationData.conversationId);
+      expect(result).toBe('Test Title');
+    });
+
+    it('should return null if conversation has no title', async () => {
+      await Conversation.create({
+        conversationId: mockConversationData.conversationId,
+        user: 'user123',
+        title: null,
+        endpoint: EModelEndpoint.openAI,
+      });
+
+      const result = await getConvoTitle('user123', mockConversationData.conversationId);
+      expect(result).toBeNull();
+    });
+
+    it('should return "New Chat" if conversation not found', async () => {
+      const result = await getConvoTitle('user123', 'non-existent-id');
+      expect(result).toBe('New Chat');
+    });
+  });
+
+  describe('getConvoFiles', () => {
+    it('should return conversation files', async () => {
+      const files = ['file1', 'file2'];
+      await Conversation.create({
+        conversationId: mockConversationData.conversationId,
+        user: 'user123',
+        endpoint: EModelEndpoint.openAI,
+        files,
+      });
+
+      const result = await getConvoFiles(mockConversationData.conversationId);
+      expect(result).toEqual(files);
+    });
+
+    it('should return empty array if no files', async () => {
+      await Conversation.create({
+        conversationId: mockConversationData.conversationId,
+        user: 'user123',
+        endpoint: EModelEndpoint.openAI,
+      });
+
+      const result = await getConvoFiles(mockConversationData.conversationId);
+      expect(result).toEqual([]);
+    });
+
+    it('should return empty array if conversation not found', async () => {
+      const result = await getConvoFiles('non-existent-id');
+      expect(result).toEqual([]);
+    });
+  });
+
+  describe('deleteConvos', () => {
+    it('should delete conversations and associated messages', async () => {
+      await Conversation.create({
+        conversationId: mockConversationData.conversationId,
+        user: 'user123',
+        title: 'To Delete',
+        endpoint: EModelEndpoint.openAI,
+      });
+
+      deleteMessages.mockResolvedValue({ deletedCount: 5 });
+
+      const result = await deleteConvos('user123', {
+        conversationId: mockConversationData.conversationId,
+      });
+
+      expect(result.deletedCount).toBe(1);
+      expect(result.messages.deletedCount).toBe(5);
+      expect(deleteMessages).toHaveBeenCalledWith({
+        conversationId: { $in: [mockConversationData.conversationId] },
+      });
+
+      // Verify conversation was deleted
+      const deletedConvo = await Conversation.findOne({
+        conversationId: mockConversationData.conversationId,
+      });
+      expect(deletedConvo).toBeNull();
+    });
+
+    it('should throw error if no conversations found', async () => {
+      await expect(deleteConvos('user123', { conversationId: 'non-existent' })).rejects.toThrow(
+        'Conversation not found or already deleted.',
+      );
+    });
+  });
+
+  describe('deleteNullOrEmptyConversations', () => {
+    it('should delete conversations with null, empty, or missing conversationIds', async () => {
+      // Since conversationId is required by the schema, we can't create documents with null/missing IDs
+      // This test should verify the function works when such documents exist (e.g., from data corruption)
+
+      // For this test, let's create a valid conversation and verify the function doesn't delete it
+      await Conversation.create({
+        conversationId: mockConversationData.conversationId,
+        user: 'user4',
+        endpoint: EModelEndpoint.openAI,
+      });
+
+      deleteMessages.mockResolvedValue({ deletedCount: 0 });
+
+      const result = await deleteNullOrEmptyConversations();
+
+      expect(result.conversations.deletedCount).toBe(0); // No invalid conversations to delete
+      expect(result.messages.deletedCount).toBe(0);
+
+      // Verify valid conversation remains
+      const remainingConvos = await Conversation.find({});
+      expect(remainingConvos).toHaveLength(1);
+      expect(remainingConvos[0].conversationId).toBe(mockConversationData.conversationId);
+    });
+  });
+
+  describe('Error Handling', () => {
+    it('should handle database errors in saveConvo', async () => {
+      // Force a database error by disconnecting
+      await mongoose.disconnect();
+
+      const result = await saveConvo(mockReq, mockConversationData);
+
+      expect(result).toEqual({ message: 'Error saving conversation' });
+
+      // Reconnect for other tests
+      await mongoose.connect(mongoServer.getUri());
+    });
+  });
+});

api/models/ConversationTag.js

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

api/models/File.js

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

api/models/File.spec.js

@@ -0,0 +1,621 @@
+const mongoose = require('mongoose');
+const { v4: uuidv4 } = require('uuid');
+const { createModels } = require('@librechat/data-schemas');
+const { MongoMemoryServer } = require('mongodb-memory-server');
+const {
+  SystemRoles,
+  ResourceType,
+  AccessRoleIds,
+  PrincipalType,
+} = require('librechat-data-provider');
+const { grantPermission } = require('~/server/services/PermissionService');
+const { getFiles, createFile } = require('./File');
+const { seedDefaultRoles } = require('~/models');
+const { createAgent } = require('./Agent');
+
+let File;
+let Agent;
+let AclEntry;
+let User;
+let modelsToCleanup = [];
+
+describe('File Access Control', () => {
+  let mongoServer;
+
+  beforeAll(async () => {
+    mongoServer = await MongoMemoryServer.create();
+    const mongoUri = mongoServer.getUri();
+    await mongoose.connect(mongoUri);
+
+    // Initialize all models
+    const models = createModels(mongoose);
+
+    // Track which models we're adding
+    modelsToCleanup = Object.keys(models);
+
+    // Register models on mongoose.models so methods can access them
+    const dbModels = require('~/db/models');
+    Object.assign(mongoose.models, dbModels);
+
+    File = dbModels.File;
+    Agent = dbModels.Agent;
+    AclEntry = dbModels.AclEntry;
+    User = dbModels.User;
+
+    // Seed default roles
+    await seedDefaultRoles();
+  });
+
+  afterAll(async () => {
+    // Clean up all collections before disconnecting
+    const collections = mongoose.connection.collections;
+    for (const key in collections) {
+      await collections[key].deleteMany({});
+    }
+
+    // Clear only the models we added
+    for (const modelName of modelsToCleanup) {
+      if (mongoose.models[modelName]) {
+        delete mongoose.models[modelName];
+      }
+    }
+
+    await mongoose.disconnect();
+    await mongoServer.stop();
+  });
+
+  beforeEach(async () => {
+    await File.deleteMany({});
+    await Agent.deleteMany({});
+    await AclEntry.deleteMany({});
+    await User.deleteMany({});
+    // Don't delete AccessRole as they are seeded defaults needed for tests
+  });
+
+  describe('hasAccessToFilesViaAgent', () => {
+    it('should efficiently check access for multiple files at once', async () => {
+      const userId = new mongoose.Types.ObjectId();
+      const authorId = new mongoose.Types.ObjectId();
+      const agentId = uuidv4();
+      const fileIds = [uuidv4(), uuidv4(), uuidv4(), uuidv4()];
+
+      // Create users
+      await User.create({
+        _id: userId,
+        email: 'user@example.com',
+        emailVerified: true,
+        provider: 'local',
+      });
+
+      await User.create({
+        _id: authorId,
+        email: 'author@example.com',
+        emailVerified: true,
+        provider: 'local',
+      });
+
+      // Create files
+      for (const fileId of fileIds) {
+        await createFile({
+          user: authorId,
+          file_id: fileId,
+          filename: `file-${fileId}.txt`,
+          filepath: `/uploads/${fileId}`,
+        });
+      }
+
+      // Create agent with only first two files attached
+      const agent = await createAgent({
+        id: agentId,
+        name: 'Test Agent',
+        author: authorId,
+        model: 'gpt-4',
+        provider: 'openai',
+        tool_resources: {
+          file_search: {
+            file_ids: [fileIds[0], fileIds[1]],
+          },
+        },
+      });
+
+      // Grant EDIT permission to user on the agent
+      await grantPermission({
+        principalType: PrincipalType.USER,
+        principalId: userId,
+        resourceType: ResourceType.AGENT,
+        resourceId: agent._id,
+        accessRoleId: AccessRoleIds.AGENT_EDITOR,
+        grantedBy: authorId,
+      });
+
+      // Check access for all files
+      const { hasAccessToFilesViaAgent } = require('~/server/services/Files/permissions');
+      const accessMap = await hasAccessToFilesViaAgent({
+        userId: userId,
+        role: SystemRoles.USER,
+        fileIds,
+        agentId: agent.id, // Use agent.id which is the custom UUID
+      });
+
+      // Should have access only to the first two files
+      expect(accessMap.get(fileIds[0])).toBe(true);
+      expect(accessMap.get(fileIds[1])).toBe(true);
+      expect(accessMap.get(fileIds[2])).toBe(false);
+      expect(accessMap.get(fileIds[3])).toBe(false);
+    });
+
+    it('should grant access to all files when user is the agent author', async () => {
+      const authorId = new mongoose.Types.ObjectId();
+      const agentId = uuidv4();
+      const fileIds = [uuidv4(), uuidv4(), uuidv4()];
+
+      // Create author user
+      await User.create({
+        _id: authorId,
+        email: 'author@example.com',
+        emailVerified: true,
+        provider: 'local',
+      });
+
+      // Create agent
+      await createAgent({
+        id: agentId,
+        name: 'Test Agent',
+        author: authorId,
+        model: 'gpt-4',
+        provider: 'openai',
+        tool_resources: {
+          file_search: {
+            file_ids: [fileIds[0]], // Only one file attached
+          },
+        },
+      });
+
+      // Check access as the author
+      const { hasAccessToFilesViaAgent } = require('~/server/services/Files/permissions');
+      const accessMap = await hasAccessToFilesViaAgent({
+        userId: authorId,
+        role: SystemRoles.USER,
+        fileIds,
+        agentId,
+      });
+
+      // Author should have access to all files
+      expect(accessMap.get(fileIds[0])).toBe(true);
+      expect(accessMap.get(fileIds[1])).toBe(true);
+      expect(accessMap.get(fileIds[2])).toBe(true);
+    });
+
+    it('should handle non-existent agent gracefully', async () => {
+      const userId = new mongoose.Types.ObjectId();
+      const fileIds = [uuidv4(), uuidv4()];
+
+      // Create user
+      await User.create({
+        _id: userId,
+        email: 'user@example.com',
+        emailVerified: true,
+        provider: 'local',
+      });
+
+      const { hasAccessToFilesViaAgent } = require('~/server/services/Files/permissions');
+      const accessMap = await hasAccessToFilesViaAgent({
+        userId: userId,
+        role: SystemRoles.USER,
+        fileIds,
+        agentId: 'non-existent-agent',
+      });
+
+      // Should have no access to any files
+      expect(accessMap.get(fileIds[0])).toBe(false);
+      expect(accessMap.get(fileIds[1])).toBe(false);
+    });
+
+    it('should deny access when user only has VIEW permission and needs access for deletion', async () => {
+      const userId = new mongoose.Types.ObjectId();
+      const authorId = new mongoose.Types.ObjectId();
+      const agentId = uuidv4();
+      const fileIds = [uuidv4(), uuidv4()];
+
+      // Create users
+      await User.create({
+        _id: userId,
+        email: 'user@example.com',
+        emailVerified: true,
+        provider: 'local',
+      });
+
+      await User.create({
+        _id: authorId,
+        email: 'author@example.com',
+        emailVerified: true,
+        provider: 'local',
+      });
+
+      // Create agent with files
+      const agent = await createAgent({
+        id: agentId,
+        name: 'View-Only Agent',
+        author: authorId,
+        model: 'gpt-4',
+        provider: 'openai',
+        tool_resources: {
+          file_search: {
+            file_ids: fileIds,
+          },
+        },
+      });
+
+      // Grant only VIEW permission to user on the agent
+      await grantPermission({
+        principalType: PrincipalType.USER,
+        principalId: userId,
+        resourceType: ResourceType.AGENT,
+        resourceId: agent._id,
+        accessRoleId: AccessRoleIds.AGENT_VIEWER,
+        grantedBy: authorId,
+      });
+
+      // Check access for files
+      const { hasAccessToFilesViaAgent } = require('~/server/services/Files/permissions');
+      const accessMap = await hasAccessToFilesViaAgent({
+        userId: userId,
+        role: SystemRoles.USER,
+        fileIds,
+        agentId,
+        isDelete: true,
+      });
+
+      // Should have no access to any files when only VIEW permission
+      expect(accessMap.get(fileIds[0])).toBe(false);
+      expect(accessMap.get(fileIds[1])).toBe(false);
+    });
+
+    it('should grant access when user has VIEW permission', async () => {
+      const userId = new mongoose.Types.ObjectId();
+      const authorId = new mongoose.Types.ObjectId();
+      const agentId = uuidv4();
+      const fileIds = [uuidv4(), uuidv4()];
+
+      // Create users
+      await User.create({
+        _id: userId,
+        email: 'user@example.com',
+        emailVerified: true,
+        provider: 'local',
+      });
+
+      await User.create({
+        _id: authorId,
+        email: 'author@example.com',
+        emailVerified: true,
+        provider: 'local',
+      });
+
+      // Create agent with files
+      const agent = await createAgent({
+        id: agentId,
+        name: 'View-Only Agent',
+        author: authorId,
+        model: 'gpt-4',
+        provider: 'openai',
+        tool_resources: {
+          file_search: {
+            file_ids: fileIds,
+          },
+        },
+      });
+
+      // Grant only VIEW permission to user on the agent
+      await grantPermission({
+        principalType: PrincipalType.USER,
+        principalId: userId,
+        resourceType: ResourceType.AGENT,
+        resourceId: agent._id,
+        accessRoleId: AccessRoleIds.AGENT_VIEWER,
+        grantedBy: authorId,
+      });
+
+      // Check access for files
+      const { hasAccessToFilesViaAgent } = require('~/server/services/Files/permissions');
+      const accessMap = await hasAccessToFilesViaAgent({
+        userId: userId,
+        role: SystemRoles.USER,
+        fileIds,
+        agentId,
+      });
+
+      expect(accessMap.get(fileIds[0])).toBe(true);
+      expect(accessMap.get(fileIds[1])).toBe(true);
+    });
+  });
+
+  describe('getFiles with agent access control', () => {
+    test('should return files owned by user and files accessible through agent', async () => {
+      const authorId = new mongoose.Types.ObjectId();
+      const userId = new mongoose.Types.ObjectId();
+      const agentId = `agent_${uuidv4()}`;
+      const ownedFileId = `file_${uuidv4()}`;
+      const sharedFileId = `file_${uuidv4()}`;
+      const inaccessibleFileId = `file_${uuidv4()}`;
+
+      // Create users
+      await User.create({
+        _id: userId,
+        email: 'user@example.com',
+        emailVerified: true,
+        provider: 'local',
+      });
+
+      await User.create({
+        _id: authorId,
+        email: 'author@example.com',
+        emailVerified: true,
+        provider: 'local',
+      });
+
+      // Create agent with shared file
+      const agent = await createAgent({
+        id: agentId,
+        name: 'Shared Agent',
+        provider: 'test',
+        model: 'test-model',
+        author: authorId,
+        tool_resources: {
+          file_search: {
+            file_ids: [sharedFileId],
+          },
+        },
+      });
+
+      // Grant EDIT permission to user on the agent
+      await grantPermission({
+        principalType: PrincipalType.USER,
+        principalId: userId,
+        resourceType: ResourceType.AGENT,
+        resourceId: agent._id,
+        accessRoleId: AccessRoleIds.AGENT_EDITOR,
+        grantedBy: authorId,
+      });
+
+      // Create files
+      await createFile({
+        file_id: ownedFileId,
+        user: userId,
+        filename: 'owned.txt',
+        filepath: '/uploads/owned.txt',
+        type: 'text/plain',
+        bytes: 100,
+      });
+
+      await createFile({
+        file_id: sharedFileId,
+        user: authorId,
+        filename: 'shared.txt',
+        filepath: '/uploads/shared.txt',
+        type: 'text/plain',
+        bytes: 200,
+        embedded: true,
+      });
+
+      await createFile({
+        file_id: inaccessibleFileId,
+        user: authorId,
+        filename: 'inaccessible.txt',
+        filepath: '/uploads/inaccessible.txt',
+        type: 'text/plain',
+        bytes: 300,
+      });
+
+      // Get all files first
+      const allFiles = await getFiles(
+        { file_id: { $in: [ownedFileId, sharedFileId, inaccessibleFileId] } },
+        null,
+        { text: 0 },
+      );
+
+      // Then filter by access control
+      const { filterFilesByAgentAccess } = require('~/server/services/Files/permissions');
+      const files = await filterFilesByAgentAccess({
+        files: allFiles,
+        userId: userId,
+        role: SystemRoles.USER,
+        agentId,
+      });
+
+      expect(files).toHaveLength(2);
+      expect(files.map((f) => f.file_id)).toContain(ownedFileId);
+      expect(files.map((f) => f.file_id)).toContain(sharedFileId);
+      expect(files.map((f) => f.file_id)).not.toContain(inaccessibleFileId);
+    });
+
+    test('should return all files when no userId/agentId provided', async () => {
+      const userId = new mongoose.Types.ObjectId();
+      const fileId1 = `file_${uuidv4()}`;
+      const fileId2 = `file_${uuidv4()}`;
+
+      await createFile({
+        file_id: fileId1,
+        user: userId,
+        filename: 'file1.txt',
+        filepath: '/uploads/file1.txt',
+        type: 'text/plain',
+        bytes: 100,
+      });
+
+      await createFile({
+        file_id: fileId2,
+        user: new mongoose.Types.ObjectId(),
+        filename: 'file2.txt',
+        filepath: '/uploads/file2.txt',
+        type: 'text/plain',
+        bytes: 200,
+      });
+
+      const files = await getFiles({ file_id: { $in: [fileId1, fileId2] } });
+      expect(files).toHaveLength(2);
+    });
+  });
+
+  describe('Role-based file permissions', () => {
+    it('should optimize permission checks when role is provided', async () => {
+      const userId = new mongoose.Types.ObjectId();
+      const authorId = new mongoose.Types.ObjectId();
+      const agentId = uuidv4();
+      const fileIds = [uuidv4(), uuidv4()];
+
+      // Create users
+      await User.create({
+        _id: userId,
+        email: 'user@example.com',
+        emailVerified: true,
+        provider: 'local',
+        role: 'ADMIN', // User has ADMIN role
+      });
+
+      await User.create({
+        _id: authorId,
+        email: 'author@example.com',
+        emailVerified: true,
+        provider: 'local',
+      });
+
+      // Create files
+      for (const fileId of fileIds) {
+        await createFile({
+          file_id: fileId,
+          user: authorId,
+          filename: `${fileId}.txt`,
+          filepath: `/uploads/${fileId}.txt`,
+          type: 'text/plain',
+          bytes: 100,
+        });
+      }
+
+      // Create agent with files
+      const agent = await createAgent({
+        id: agentId,
+        name: 'Test Agent',
+        author: authorId,
+        model: 'gpt-4',
+        provider: 'openai',
+        tool_resources: {
+          file_search: {
+            file_ids: fileIds,
+          },
+        },
+      });
+
+      // Grant permission to ADMIN role
+      await grantPermission({
+        principalType: PrincipalType.ROLE,
+        principalId: 'ADMIN',
+        resourceType: ResourceType.AGENT,
+        resourceId: agent._id,
+        accessRoleId: AccessRoleIds.AGENT_EDITOR,
+        grantedBy: authorId,
+      });
+
+      // Check access with role provided (should avoid DB query)
+      const { hasAccessToFilesViaAgent } = require('~/server/services/Files/permissions');
+      const accessMapWithRole = await hasAccessToFilesViaAgent({
+        userId: userId,
+        role: 'ADMIN',
+        fileIds,
+        agentId: agent.id,
+      });
+
+      // User should have access through their ADMIN role
+      expect(accessMapWithRole.get(fileIds[0])).toBe(true);
+      expect(accessMapWithRole.get(fileIds[1])).toBe(true);
+
+      // Check access without role (will query DB to get user's role)
+      const accessMapWithoutRole = await hasAccessToFilesViaAgent({
+        userId: userId,
+        fileIds,
+        agentId: agent.id,
+      });
+
+      // Should have same result
+      expect(accessMapWithoutRole.get(fileIds[0])).toBe(true);
+      expect(accessMapWithoutRole.get(fileIds[1])).toBe(true);
+    });
+
+    it('should deny access when user role changes', async () => {
+      const userId = new mongoose.Types.ObjectId();
+      const authorId = new mongoose.Types.ObjectId();
+      const agentId = uuidv4();
+      const fileId = uuidv4();
+
+      // Create users
+      await User.create({
+        _id: userId,
+        email: 'user@example.com',
+        emailVerified: true,
+        provider: 'local',
+        role: 'EDITOR',
+      });
+
+      await User.create({
+        _id: authorId,
+        email: 'author@example.com',
+        emailVerified: true,
+        provider: 'local',
+      });
+
+      // Create file
+      await createFile({
+        file_id: fileId,
+        user: authorId,
+        filename: 'test.txt',
+        filepath: '/uploads/test.txt',
+        type: 'text/plain',
+        bytes: 100,
+      });
+
+      // Create agent
+      const agent = await createAgent({
+        id: agentId,
+        name: 'Test Agent',
+        author: authorId,
+        model: 'gpt-4',
+        provider: 'openai',
+        tool_resources: {
+          file_search: {
+            file_ids: [fileId],
+          },
+        },
+      });
+
+      // Grant permission to EDITOR role only
+      await grantPermission({
+        principalType: PrincipalType.ROLE,
+        principalId: 'EDITOR',
+        resourceType: ResourceType.AGENT,
+        resourceId: agent._id,
+        accessRoleId: AccessRoleIds.AGENT_EDITOR,
+        grantedBy: authorId,
+      });
+
+      const { hasAccessToFilesViaAgent } = require('~/server/services/Files/permissions');
+
+      // Check with EDITOR role - should have access
+      const accessAsEditor = await hasAccessToFilesViaAgent({
+        userId: userId,
+        role: 'EDITOR',
+        fileIds: [fileId],
+        agentId: agent.id,
+      });
+      expect(accessAsEditor.get(fileId)).toBe(true);
+
+      // Simulate role change to USER - should lose access
+      const accessAsUser = await hasAccessToFilesViaAgent({
+        userId: userId,
+        role: SystemRoles.USER,
+        fileIds: [fileId],
+        agentId: agent.id,
+      });
+      expect(accessAsUser.get(fileId)).toBe(false);
+    });
+  });
+});

api/models/Message.js

@@ -1,7 +1,6 @@
 const { z } = require('zod');
 const { logger } = require('@librechat/data-schemas');
 const { createTempChatExpirationDate } = require('@librechat/api');
-const getCustomConfig = require('~/server/services/Config/loadCustomConfig');
 const { Message } = require('~/db/models');
 
 const idSchema = z.string().uuid();
@@ -11,7 +10,7 @@ const idSchema = z.string().uuid();
  *
  * @async
  * @function saveMessage
- * @param {Express.Request} req - The request object containing user information.
+ * @param {ServerRequest} req - The request object containing user information.
  * @param {Object} params - The message data object.
  * @param {string} params.endpoint - The endpoint where the message originated.
  * @param {string} params.iconURL - The URL of the sender's icon.
@@ -57,8 +56,8 @@ async function saveMessage(req, params, metadata) {
 
     if (req?.body?.isTemporary) {
       try {
-        const customConfig = await getCustomConfig();
-        update.expiredAt = createTempChatExpirationDate(customConfig);
+        const appConfig = req.config;
+        update.expiredAt = createTempChatExpirationDate(appConfig?.interfaceConfig);
       } catch (err) {
         logger.error('Error creating temporary chat expiration date:', err);
         logger.info(`---\`saveMessage\` context: ${metadata?.context}`);

api/models/Message.spec.js

@@ -1,17 +1,20 @@
 const mongoose = require('mongoose');
-const { MongoMemoryServer } = require('mongodb-memory-server');
 const { v4: uuidv4 } = require('uuid');
 const { messageSchema } = require('@librechat/data-schemas');
+const { MongoMemoryServer } = require('mongodb-memory-server');
 
 const {
   saveMessage,
   getMessages,
   updateMessage,
   deleteMessages,
+  bulkSaveMessages,
   updateMessageText,
   deleteMessagesSince,
 } = require('./Message');
 
+jest.mock('~/server/services/Config/app');
+
 /**
  * @type {import('mongoose').Model<import('@librechat/data-schemas').IMessage>}
  */
@@ -40,6 +43,11 @@ describe('Message Operations', () => {
 
     mockReq = {
       user: { id: 'user123' },
+      config: {
+        interfaceConfig: {
+          temporaryChatRetention: 24, // Default 24 hours
+        },
+      },
     };
 
     mockMessageData = {
@@ -117,21 +125,21 @@ describe('Message Operations', () => {
       const conversationId = uuidv4();
 
       // Create multiple messages in the same conversation
-      const message1 = await saveMessage(mockReq, {
+      await saveMessage(mockReq, {
         messageId: 'msg1',
         conversationId,
         text: 'First message',
         user: 'user123',
       });
 
-      const message2 = await saveMessage(mockReq, {
+      await saveMessage(mockReq, {
         messageId: 'msg2',
         conversationId,
         text: 'Second message',
         user: 'user123',
       });
 
-      const message3 = await saveMessage(mockReq, {
+      await saveMessage(mockReq, {
         messageId: 'msg3',
         conversationId,
         text: 'Third message',
@@ -314,4 +322,255 @@ describe('Message Operations', () => {
       expect(messages[0].text).toBe('Victim message');
     });
   });
+
+  describe('isTemporary message handling', () => {
+    beforeEach(() => {
+      // Reset mocks before each test
+      jest.clearAllMocks();
+    });
+
+    it('should save a message with expiredAt when isTemporary is true', async () => {
+      // Mock app config with 24 hour retention
+      mockReq.config.interfaceConfig.temporaryChatRetention = 24;
+
+      mockReq.body = { isTemporary: true };
+
+      const beforeSave = new Date();
+      const result = await saveMessage(mockReq, mockMessageData);
+      const afterSave = new Date();
+
+      expect(result.messageId).toBe('msg123');
+      expect(result.expiredAt).toBeDefined();
+      expect(result.expiredAt).toBeInstanceOf(Date);
+
+      // Verify expiredAt is approximately 24 hours in the future
+      const expectedExpirationTime = new Date(beforeSave.getTime() + 24 * 60 * 60 * 1000);
+      const actualExpirationTime = new Date(result.expiredAt);
+
+      expect(actualExpirationTime.getTime()).toBeGreaterThanOrEqual(
+        expectedExpirationTime.getTime() - 1000,
+      );
+      expect(actualExpirationTime.getTime()).toBeLessThanOrEqual(
+        new Date(afterSave.getTime() + 24 * 60 * 60 * 1000 + 1000).getTime(),
+      );
+    });
+
+    it('should save a message without expiredAt when isTemporary is false', async () => {
+      mockReq.body = { isTemporary: false };
+
+      const result = await saveMessage(mockReq, mockMessageData);
+
+      expect(result.messageId).toBe('msg123');
+      expect(result.expiredAt).toBeNull();
+    });
+
+    it('should save a message without expiredAt when isTemporary is not provided', async () => {
+      // No isTemporary in body
+      mockReq.body = {};
+
+      const result = await saveMessage(mockReq, mockMessageData);
+
+      expect(result.messageId).toBe('msg123');
+      expect(result.expiredAt).toBeNull();
+    });
+
+    it('should use custom retention period from config', async () => {
+      // Mock app config with 48 hour retention
+      mockReq.config.interfaceConfig.temporaryChatRetention = 48;
+
+      mockReq.body = { isTemporary: true };
+
+      const beforeSave = new Date();
+      const result = await saveMessage(mockReq, mockMessageData);
+
+      expect(result.expiredAt).toBeDefined();
+
+      // Verify expiredAt is approximately 48 hours in the future
+      const expectedExpirationTime = new Date(beforeSave.getTime() + 48 * 60 * 60 * 1000);
+      const actualExpirationTime = new Date(result.expiredAt);
+
+      expect(actualExpirationTime.getTime()).toBeGreaterThanOrEqual(
+        expectedExpirationTime.getTime() - 1000,
+      );
+      expect(actualExpirationTime.getTime()).toBeLessThanOrEqual(
+        expectedExpirationTime.getTime() + 1000,
+      );
+    });
+
+    it('should handle minimum retention period (1 hour)', async () => {
+      // Mock app config with less than minimum retention
+      mockReq.config.interfaceConfig.temporaryChatRetention = 0.5; // Half hour - should be clamped to 1 hour
+
+      mockReq.body = { isTemporary: true };
+
+      const beforeSave = new Date();
+      const result = await saveMessage(mockReq, mockMessageData);
+
+      expect(result.expiredAt).toBeDefined();
+
+      // Verify expiredAt is approximately 1 hour in the future (minimum)
+      const expectedExpirationTime = new Date(beforeSave.getTime() + 1 * 60 * 60 * 1000);
+      const actualExpirationTime = new Date(result.expiredAt);
+
+      expect(actualExpirationTime.getTime()).toBeGreaterThanOrEqual(
+        expectedExpirationTime.getTime() - 1000,
+      );
+      expect(actualExpirationTime.getTime()).toBeLessThanOrEqual(
+        expectedExpirationTime.getTime() + 1000,
+      );
+    });
+
+    it('should handle maximum retention period (8760 hours)', async () => {
+      // Mock app config with more than maximum retention
+      mockReq.config.interfaceConfig.temporaryChatRetention = 10000; // Should be clamped to 8760 hours
+
+      mockReq.body = { isTemporary: true };
+
+      const beforeSave = new Date();
+      const result = await saveMessage(mockReq, mockMessageData);
+
+      expect(result.expiredAt).toBeDefined();
+
+      // Verify expiredAt is approximately 8760 hours (1 year) in the future
+      const expectedExpirationTime = new Date(beforeSave.getTime() + 8760 * 60 * 60 * 1000);
+      const actualExpirationTime = new Date(result.expiredAt);
+
+      expect(actualExpirationTime.getTime()).toBeGreaterThanOrEqual(
+        expectedExpirationTime.getTime() - 1000,
+      );
+      expect(actualExpirationTime.getTime()).toBeLessThanOrEqual(
+        expectedExpirationTime.getTime() + 1000,
+      );
+    });
+
+    it('should handle missing config gracefully', async () => {
+      // Simulate missing config - should use default retention period
+      delete mockReq.config;
+
+      mockReq.body = { isTemporary: true };
+
+      const beforeSave = new Date();
+      const result = await saveMessage(mockReq, mockMessageData);
+      const afterSave = new Date();
+
+      // Should still save the message with default retention period (30 days)
+      expect(result.messageId).toBe('msg123');
+      expect(result.expiredAt).toBeDefined();
+      expect(result.expiredAt).toBeInstanceOf(Date);
+
+      // Verify expiredAt is approximately 30 days in the future (720 hours)
+      const expectedExpirationTime = new Date(beforeSave.getTime() + 720 * 60 * 60 * 1000);
+      const actualExpirationTime = new Date(result.expiredAt);
+
+      expect(actualExpirationTime.getTime()).toBeGreaterThanOrEqual(
+        expectedExpirationTime.getTime() - 1000,
+      );
+      expect(actualExpirationTime.getTime()).toBeLessThanOrEqual(
+        new Date(afterSave.getTime() + 720 * 60 * 60 * 1000 + 1000).getTime(),
+      );
+    });
+
+    it('should use default retention when config is not provided', async () => {
+      // Mock getAppConfig to return empty config
+      mockReq.config = {}; // Empty config
+
+      mockReq.body = { isTemporary: true };
+
+      const beforeSave = new Date();
+      const result = await saveMessage(mockReq, mockMessageData);
+
+      expect(result.expiredAt).toBeDefined();
+
+      // Default retention is 30 days (720 hours)
+      const expectedExpirationTime = new Date(beforeSave.getTime() + 30 * 24 * 60 * 60 * 1000);
+      const actualExpirationTime = new Date(result.expiredAt);
+
+      expect(actualExpirationTime.getTime()).toBeGreaterThanOrEqual(
+        expectedExpirationTime.getTime() - 1000,
+      );
+      expect(actualExpirationTime.getTime()).toBeLessThanOrEqual(
+        expectedExpirationTime.getTime() + 1000,
+      );
+    });
+
+    it('should not update expiredAt on message update', async () => {
+      // First save a temporary message
+      mockReq.config.interfaceConfig.temporaryChatRetention = 24;
+
+      mockReq.body = { isTemporary: true };
+      const savedMessage = await saveMessage(mockReq, mockMessageData);
+      const originalExpiredAt = savedMessage.expiredAt;
+
+      // Now update the message without isTemporary flag
+      mockReq.body = {};
+      const updatedMessage = await updateMessage(mockReq, {
+        messageId: 'msg123',
+        text: 'Updated text',
+      });
+
+      // expiredAt should not be in the returned updated message object
+      expect(updatedMessage.expiredAt).toBeUndefined();
+
+      // Verify in database that expiredAt wasn't changed
+      const dbMessage = await Message.findOne({ messageId: 'msg123', user: 'user123' });
+      expect(dbMessage.expiredAt).toEqual(originalExpiredAt);
+    });
+
+    it('should preserve expiredAt when saving existing temporary message', async () => {
+      // First save a temporary message
+      mockReq.config.interfaceConfig.temporaryChatRetention = 24;
+
+      mockReq.body = { isTemporary: true };
+      const firstSave = await saveMessage(mockReq, mockMessageData);
+      const originalExpiredAt = firstSave.expiredAt;
+
+      // Wait a bit to ensure time difference
+      await new Promise((resolve) => setTimeout(resolve, 100));
+
+      // Save again with same messageId but different text
+      const updatedData = { ...mockMessageData, text: 'Updated text' };
+      const secondSave = await saveMessage(mockReq, updatedData);
+
+      // Should update text but create new expiredAt
+      expect(secondSave.text).toBe('Updated text');
+      expect(secondSave.expiredAt).toBeDefined();
+      expect(new Date(secondSave.expiredAt).getTime()).toBeGreaterThan(
+        new Date(originalExpiredAt).getTime(),
+      );
+    });
+
+    it('should handle bulk operations with temporary messages', async () => {
+      // This test verifies bulkSaveMessages doesn't interfere with expiredAt
+      const messages = [
+        {
+          messageId: 'bulk1',
+          conversationId: uuidv4(),
+          text: 'Bulk message 1',
+          user: 'user123',
+          expiredAt: new Date(Date.now() + 24 * 60 * 60 * 1000),
+        },
+        {
+          messageId: 'bulk2',
+          conversationId: uuidv4(),
+          text: 'Bulk message 2',
+          user: 'user123',
+          expiredAt: null,
+        },
+      ];
+
+      await bulkSaveMessages(messages);
+
+      const savedMessages = await Message.find({
+        messageId: { $in: ['bulk1', 'bulk2'] },
+      }).lean();
+
+      expect(savedMessages).toHaveLength(2);
+
+      const bulk1 = savedMessages.find((m) => m.messageId === 'bulk1');
+      const bulk2 = savedMessages.find((m) => m.messageId === 'bulk2');
+
+      expect(bulk1.expiredAt).toBeDefined();
+      expect(bulk2.expiredAt).toBeNull();
+    });
+  });
 });

api/models/Prompt.js

@@ -1,12 +1,18 @@
 const { ObjectId } = require('mongodb');
 const { logger } = require('@librechat/data-schemas');
-const { SystemRoles, SystemCategories, Constants } = require('librechat-data-provider');
 const {
-  getProjectByName,
-  addGroupIdsToProject,
-  removeGroupIdsFromProject,
+  Constants,
+  SystemRoles,
+  ResourceType,
+  SystemCategories,
+} = require('librechat-data-provider');
+const {
   removeGroupFromAllProjects,
+  removeGroupIdsFromProject,
+  addGroupIdsToProject,
+  getProjectByName,
 } = require('./Project');
+const { removeAllPermissions } = require('~/server/services/PermissionService');
 const { PromptGroup, Prompt } = require('~/db/models');
 const { escapeRegExp } = require('~/server/utils');
 
@@ -100,10 +106,6 @@ const getAllPromptGroups = async (req, filter) => {
   try {
     const { name, ...query } = filter;
 
-    if (!query.author) {
-      throw new Error('Author is required');
-    }
-
     let searchShared = true;
     let searchSharedOnly = false;
     if (name) {
@@ -153,10 +155,6 @@ const getPromptGroups = async (req, filter) => {
     const validatedPageNumber = Math.max(parseInt(pageNumber, 10), 1);
     const validatedPageSize = Math.max(parseInt(pageSize, 10), 1);
 
-    if (!query.author) {
-      throw new Error('Author is required');
-    }
-
     let searchShared = true;
     let searchSharedOnly = false;
     if (name) {
@@ -221,12 +219,16 @@ const getPromptGroups = async (req, filter) => {
  * @returns {Promise<TDeletePromptGroupResponse>}
  */
 const deletePromptGroup = async ({ _id, author, role }) => {
-  const query = { _id, author };
-  const groupQuery = { groupId: new ObjectId(_id), author };
-  if (role === SystemRoles.ADMIN) {
-    delete query.author;
-    delete groupQuery.author;
+  // Build query - with ACL, author is optional
+  const query = { _id };
+  const groupQuery = { groupId: new ObjectId(_id) };
+
+  // Legacy: Add author filter if provided (backward compatibility)
+  if (author && role !== SystemRoles.ADMIN) {
+    query.author = author;
+    groupQuery.author = author;
   }
+
   const response = await PromptGroup.deleteOne(query);
 
   if (!response || response.deletedCount === 0) {
@@ -235,13 +237,140 @@ const deletePromptGroup = async ({ _id, author, role }) => {
 
   await Prompt.deleteMany(groupQuery);
   await removeGroupFromAllProjects(_id);
+
+  try {
+    await removeAllPermissions({ resourceType: ResourceType.PROMPTGROUP, resourceId: _id });
+  } catch (error) {
+    logger.error('Error removing promptGroup permissions:', error);
+  }
+
   return { message: 'Prompt group deleted successfully' };
 };
 
+/**
+ * Get prompt groups by accessible IDs with optional cursor-based pagination.
+ * @param {Object} params - The parameters for getting accessible prompt groups.
+ * @param {Array} [params.accessibleIds] - Array of prompt group ObjectIds the user has ACL access to.
+ * @param {Object} [params.otherParams] - Additional query parameters (including author filter).
+ * @param {number} [params.limit] - Number of prompt groups to return (max 100). If not provided, returns all prompt groups.
+ * @param {string} [params.after] - Cursor for pagination - get prompt groups after this cursor. // base64 encoded JSON string with updatedAt and _id.
+ * @returns {Promise<Object>} A promise that resolves to an object containing the prompt groups data and pagination info.
+ */
+async function getListPromptGroupsByAccess({
+  accessibleIds = [],
+  otherParams = {},
+  limit = null,
+  after = null,
+}) {
+  const isPaginated = limit !== null && limit !== undefined;
+  const normalizedLimit = isPaginated ? Math.min(Math.max(1, parseInt(limit) || 20), 100) : null;
+
+  // Build base query combining ACL accessible prompt groups with other filters
+  const baseQuery = { ...otherParams, _id: { $in: accessibleIds } };
+
+  // Add cursor condition
+  if (after && typeof after === 'string' && after !== 'undefined' && after !== 'null') {
+    try {
+      const cursor = JSON.parse(Buffer.from(after, 'base64').toString('utf8'));
+      const { updatedAt, _id } = cursor;
+
+      const cursorCondition = {
+        $or: [
+          { updatedAt: { $lt: new Date(updatedAt) } },
+          { updatedAt: new Date(updatedAt), _id: { $gt: new ObjectId(_id) } },
+        ],
+      };
+
+      // Merge cursor condition with base query
+      if (Object.keys(baseQuery).length > 0) {
+        baseQuery.$and = [{ ...baseQuery }, cursorCondition];
+        // Remove the original conditions from baseQuery to avoid duplication
+        Object.keys(baseQuery).forEach((key) => {
+          if (key !== '$and') delete baseQuery[key];
+        });
+      } else {
+        Object.assign(baseQuery, cursorCondition);
+      }
+    } catch (error) {
+      logger.warn('Invalid cursor:', error.message);
+    }
+  }
+
+  // Build aggregation pipeline
+  const pipeline = [{ $match: baseQuery }, { $sort: { updatedAt: -1, _id: 1 } }];
+
+  // Only apply limit if pagination is requested
+  if (isPaginated) {
+    pipeline.push({ $limit: normalizedLimit + 1 });
+  }
+
+  // Add lookup for production prompt
+  pipeline.push(
+    {
+      $lookup: {
+        from: 'prompts',
+        localField: 'productionId',
+        foreignField: '_id',
+        as: 'productionPrompt',
+      },
+    },
+    { $unwind: { path: '$productionPrompt', preserveNullAndEmptyArrays: true } },
+    {
+      $project: {
+        name: 1,
+        numberOfGenerations: 1,
+        oneliner: 1,
+        category: 1,
+        projectIds: 1,
+        productionId: 1,
+        author: 1,
+        authorName: 1,
+        createdAt: 1,
+        updatedAt: 1,
+        'productionPrompt.prompt': 1,
+      },
+    },
+  );
+
+  const promptGroups = await PromptGroup.aggregate(pipeline).exec();
+
+  const hasMore = isPaginated ? promptGroups.length > normalizedLimit : false;
+  const data = (isPaginated ? promptGroups.slice(0, normalizedLimit) : promptGroups).map(
+    (group) => {
+      if (group.author) {
+        group.author = group.author.toString();
+      }
+      return group;
+    },
+  );
+
+  // Generate next cursor only if paginated
+  let nextCursor = null;
+  if (isPaginated && hasMore && data.length > 0) {
+    const lastGroup = promptGroups[normalizedLimit - 1];
+    nextCursor = Buffer.from(
+      JSON.stringify({
+        updatedAt: lastGroup.updatedAt.toISOString(),
+        _id: lastGroup._id.toString(),
+      }),
+    ).toString('base64');
+  }
+
+  return {
+    object: 'list',
+    data,
+    first_id: data.length > 0 ? data[0]._id.toString() : null,
+    last_id: data.length > 0 ? data[data.length - 1]._id.toString() : null,
+    has_more: hasMore,
+    after: nextCursor,
+  };
+}
+
 module.exports = {
   getPromptGroups,
   deletePromptGroup,
   getAllPromptGroups,
+  getListPromptGroupsByAccess,
   /**
    * Create a prompt and its respective group
    * @param {TCreatePromptRecord} saveData
@@ -430,6 +559,16 @@ module.exports = {
       .lean();
 
     if (remainingPrompts.length === 0) {
+      // Remove all ACL entries for the promptGroup when deleting the last prompt
+      try {
+        await removeAllPermissions({
+          resourceType: ResourceType.PROMPTGROUP,
+          resourceId: groupId,
+        });
+      } catch (error) {
+        logger.error('Error removing promptGroup permissions:', error);
+      }
+
       await PromptGroup.deleteOne({ _id: groupId });
       await removeGroupFromAllProjects(groupId);
 

api/models/Prompt.spec.js

@@ -0,0 +1,564 @@
+const mongoose = require('mongoose');
+const { ObjectId } = require('mongodb');
+const { logger } = require('@librechat/data-schemas');
+const { MongoMemoryServer } = require('mongodb-memory-server');
+const {
+  SystemRoles,
+  ResourceType,
+  AccessRoleIds,
+  PrincipalType,
+  PermissionBits,
+} = require('librechat-data-provider');
+
+// Mock the config/connect module to prevent connection attempts during tests
+jest.mock('../../config/connect', () => jest.fn().mockResolvedValue(true));
+
+const dbModels = require('~/db/models');
+
+// Disable console for tests
+logger.silent = true;
+
+let mongoServer;
+let Prompt, PromptGroup, AclEntry, AccessRole, User, Group, Project;
+let promptFns, permissionService;
+let testUsers, testGroups, testRoles;
+
+beforeAll(async () => {
+  // Set up MongoDB memory server
+  mongoServer = await MongoMemoryServer.create();
+  const mongoUri = mongoServer.getUri();
+  await mongoose.connect(mongoUri);
+
+  // Initialize models
+  Prompt = dbModels.Prompt;
+  PromptGroup = dbModels.PromptGroup;
+  AclEntry = dbModels.AclEntry;
+  AccessRole = dbModels.AccessRole;
+  User = dbModels.User;
+  Group = dbModels.Group;
+  Project = dbModels.Project;
+
+  promptFns = require('~/models/Prompt');
+  permissionService = require('~/server/services/PermissionService');
+
+  // Create test data
+  await setupTestData();
+});
+
+afterAll(async () => {
+  await mongoose.disconnect();
+  await mongoServer.stop();
+  jest.clearAllMocks();
+});
+
+async function setupTestData() {
+  // Create access roles for promptGroups
+  testRoles = {
+    viewer: await AccessRole.create({
+      accessRoleId: AccessRoleIds.PROMPTGROUP_VIEWER,
+      name: 'Viewer',
+      description: 'Can view promptGroups',
+      resourceType: ResourceType.PROMPTGROUP,
+      permBits: PermissionBits.VIEW,
+    }),
+    editor: await AccessRole.create({
+      accessRoleId: AccessRoleIds.PROMPTGROUP_EDITOR,
+      name: 'Editor',
+      description: 'Can view and edit promptGroups',
+      resourceType: ResourceType.PROMPTGROUP,
+      permBits: PermissionBits.VIEW | PermissionBits.EDIT,
+    }),
+    owner: await AccessRole.create({
+      accessRoleId: AccessRoleIds.PROMPTGROUP_OWNER,
+      name: 'Owner',
+      description: 'Full control over promptGroups',
+      resourceType: ResourceType.PROMPTGROUP,
+      permBits:
+        PermissionBits.VIEW | PermissionBits.EDIT | PermissionBits.DELETE | PermissionBits.SHARE,
+    }),
+  };
+
+  // Create test users
+  testUsers = {
+    owner: await User.create({
+      name: 'Prompt Owner',
+      email: 'owner@example.com',
+      role: SystemRoles.USER,
+    }),
+    editor: await User.create({
+      name: 'Prompt Editor',
+      email: 'editor@example.com',
+      role: SystemRoles.USER,
+    }),
+    viewer: await User.create({
+      name: 'Prompt Viewer',
+      email: 'viewer@example.com',
+      role: SystemRoles.USER,
+    }),
+    admin: await User.create({
+      name: 'Admin User',
+      email: 'admin@example.com',
+      role: SystemRoles.ADMIN,
+    }),
+    noAccess: await User.create({
+      name: 'No Access User',
+      email: 'noaccess@example.com',
+      role: SystemRoles.USER,
+    }),
+  };
+
+  // Create test groups
+  testGroups = {
+    editors: await Group.create({
+      name: 'Prompt Editors',
+      description: 'Group with editor access',
+    }),
+    viewers: await Group.create({
+      name: 'Prompt Viewers',
+      description: 'Group with viewer access',
+    }),
+  };
+
+  await Project.create({
+    name: 'Global',
+    description: 'Global project',
+    promptGroupIds: [],
+  });
+}
+
+describe('Prompt ACL Permissions', () => {
+  describe('Creating Prompts with Permissions', () => {
+    it('should grant owner permissions when creating a prompt', async () => {
+      // First create a group
+      const testGroup = await PromptGroup.create({
+        name: 'Test Group',
+        category: 'testing',
+        author: testUsers.owner._id,
+        authorName: testUsers.owner.name,
+        productionId: new mongoose.Types.ObjectId(),
+      });
+
+      const promptData = {
+        prompt: {
+          prompt: 'Test prompt content',
+          name: 'Test Prompt',
+          type: 'text',
+          groupId: testGroup._id,
+        },
+        author: testUsers.owner._id,
+      };
+
+      await promptFns.savePrompt(promptData);
+
+      // Manually grant permissions as would happen in the route
+      await permissionService.grantPermission({
+        principalType: PrincipalType.USER,
+        principalId: testUsers.owner._id,
+        resourceType: ResourceType.PROMPTGROUP,
+        resourceId: testGroup._id,
+        accessRoleId: AccessRoleIds.PROMPTGROUP_OWNER,
+        grantedBy: testUsers.owner._id,
+      });
+
+      // Check ACL entry
+      const aclEntry = await AclEntry.findOne({
+        resourceType: ResourceType.PROMPTGROUP,
+        resourceId: testGroup._id,
+        principalType: PrincipalType.USER,
+        principalId: testUsers.owner._id,
+      });
+
+      expect(aclEntry).toBeTruthy();
+      expect(aclEntry.permBits).toBe(testRoles.owner.permBits);
+    });
+  });
+
+  describe('Accessing Prompts', () => {
+    let testPromptGroup;
+
+    beforeEach(async () => {
+      // Create a prompt group
+      testPromptGroup = await PromptGroup.create({
+        name: 'Test Group',
+        author: testUsers.owner._id,
+        authorName: testUsers.owner.name,
+        productionId: new ObjectId(),
+      });
+
+      // Create a prompt
+      await Prompt.create({
+        prompt: 'Test prompt for access control',
+        name: 'Access Test Prompt',
+        author: testUsers.owner._id,
+        groupId: testPromptGroup._id,
+        type: 'text',
+      });
+
+      // Grant owner permissions
+      await permissionService.grantPermission({
+        principalType: PrincipalType.USER,
+        principalId: testUsers.owner._id,
+        resourceType: ResourceType.PROMPTGROUP,
+        resourceId: testPromptGroup._id,
+        accessRoleId: AccessRoleIds.PROMPTGROUP_OWNER,
+        grantedBy: testUsers.owner._id,
+      });
+    });
+
+    afterEach(async () => {
+      await Prompt.deleteMany({});
+      await PromptGroup.deleteMany({});
+      await AclEntry.deleteMany({});
+    });
+
+    it('owner should have full access to their prompt', async () => {
+      const hasAccess = await permissionService.checkPermission({
+        userId: testUsers.owner._id,
+        resourceType: ResourceType.PROMPTGROUP,
+        resourceId: testPromptGroup._id,
+        requiredPermission: PermissionBits.VIEW,
+      });
+
+      expect(hasAccess).toBe(true);
+
+      const canEdit = await permissionService.checkPermission({
+        userId: testUsers.owner._id,
+        resourceType: ResourceType.PROMPTGROUP,
+        resourceId: testPromptGroup._id,
+        requiredPermission: PermissionBits.EDIT,
+      });
+
+      expect(canEdit).toBe(true);
+    });
+
+    it('user with viewer role should only have view access', async () => {
+      // Grant viewer permissions
+      await permissionService.grantPermission({
+        principalType: PrincipalType.USER,
+        principalId: testUsers.viewer._id,
+        resourceType: ResourceType.PROMPTGROUP,
+        resourceId: testPromptGroup._id,
+        accessRoleId: AccessRoleIds.PROMPTGROUP_VIEWER,
+        grantedBy: testUsers.owner._id,
+      });
+
+      const canView = await permissionService.checkPermission({
+        userId: testUsers.viewer._id,
+        resourceType: ResourceType.PROMPTGROUP,
+        resourceId: testPromptGroup._id,
+        requiredPermission: PermissionBits.VIEW,
+      });
+
+      const canEdit = await permissionService.checkPermission({
+        userId: testUsers.viewer._id,
+        resourceType: ResourceType.PROMPTGROUP,
+        resourceId: testPromptGroup._id,
+        requiredPermission: PermissionBits.EDIT,
+      });
+
+      expect(canView).toBe(true);
+      expect(canEdit).toBe(false);
+    });
+
+    it('user without permissions should have no access', async () => {
+      const hasAccess = await permissionService.checkPermission({
+        userId: testUsers.noAccess._id,
+        resourceType: ResourceType.PROMPTGROUP,
+        resourceId: testPromptGroup._id,
+        requiredPermission: PermissionBits.VIEW,
+      });
+
+      expect(hasAccess).toBe(false);
+    });
+
+    it('admin should have access regardless of permissions', async () => {
+      // Admin users should work through normal permission system
+      // The middleware layer handles admin bypass, not the permission service
+      const hasAccess = await permissionService.checkPermission({
+        userId: testUsers.admin._id,
+        resourceType: ResourceType.PROMPTGROUP,
+        resourceId: testPromptGroup._id,
+        requiredPermission: PermissionBits.VIEW,
+      });
+
+      // Without explicit permissions, even admin won't have access at this layer
+      expect(hasAccess).toBe(false);
+
+      // The actual admin bypass happens in the middleware layer (`canAccessPromptViaGroup`/`canAccessPromptGroupResource`)
+      // which checks req.user.role === SystemRoles.ADMIN
+    });
+  });
+
+  describe('Group-based Access', () => {
+    let testPromptGroup;
+
+    beforeEach(async () => {
+      // Create a prompt group first
+      testPromptGroup = await PromptGroup.create({
+        name: 'Group Access Test Group',
+        author: testUsers.owner._id,
+        authorName: testUsers.owner.name,
+        productionId: new ObjectId(),
+      });
+
+      await Prompt.create({
+        prompt: 'Group access test prompt',
+        name: 'Group Test',
+        author: testUsers.owner._id,
+        groupId: testPromptGroup._id,
+        type: 'text',
+      });
+
+      // Add users to groups
+      await User.findByIdAndUpdate(testUsers.editor._id, {
+        $push: { groups: testGroups.editors._id },
+      });
+
+      await User.findByIdAndUpdate(testUsers.viewer._id, {
+        $push: { groups: testGroups.viewers._id },
+      });
+    });
+
+    afterEach(async () => {
+      await Prompt.deleteMany({});
+      await AclEntry.deleteMany({});
+      await User.updateMany({}, { $set: { groups: [] } });
+    });
+
+    it('group members should inherit group permissions', async () => {
+      // Create a prompt group
+      const testPromptGroup = await PromptGroup.create({
+        name: 'Group Test Group',
+        author: testUsers.owner._id,
+        authorName: testUsers.owner.name,
+        productionId: new ObjectId(),
+      });
+
+      const { addUserToGroup } = require('~/models');
+      await addUserToGroup(testUsers.editor._id, testGroups.editors._id);
+
+      const prompt = await promptFns.savePrompt({
+        author: testUsers.owner._id,
+        prompt: {
+          prompt: 'Group test prompt',
+          name: 'Group Test',
+          groupId: testPromptGroup._id,
+          type: 'text',
+        },
+      });
+
+      // Check if savePrompt returned an error
+      if (!prompt || !prompt.prompt) {
+        throw new Error(`Failed to save prompt: ${prompt?.message || 'Unknown error'}`);
+      }
+
+      // Grant edit permissions to the group
+      await permissionService.grantPermission({
+        principalType: PrincipalType.GROUP,
+        principalId: testGroups.editors._id,
+        resourceType: ResourceType.PROMPTGROUP,
+        resourceId: testPromptGroup._id,
+        accessRoleId: AccessRoleIds.PROMPTGROUP_EDITOR,
+        grantedBy: testUsers.owner._id,
+      });
+
+      // Check if group member has access
+      const hasAccess = await permissionService.checkPermission({
+        userId: testUsers.editor._id,
+        resourceType: ResourceType.PROMPTGROUP,
+        resourceId: testPromptGroup._id,
+        requiredPermission: PermissionBits.EDIT,
+      });
+
+      expect(hasAccess).toBe(true);
+
+      // Check that non-member doesn't have access
+      const nonMemberAccess = await permissionService.checkPermission({
+        userId: testUsers.viewer._id,
+        resourceType: ResourceType.PROMPTGROUP,
+        resourceId: testPromptGroup._id,
+        requiredPermission: PermissionBits.EDIT,
+      });
+
+      expect(nonMemberAccess).toBe(false);
+    });
+  });
+
+  describe('Public Access', () => {
+    let publicPromptGroup, privatePromptGroup;
+
+    beforeEach(async () => {
+      // Create separate prompt groups for public and private access
+      publicPromptGroup = await PromptGroup.create({
+        name: 'Public Access Test Group',
+        author: testUsers.owner._id,
+        authorName: testUsers.owner.name,
+        productionId: new ObjectId(),
+      });
+
+      privatePromptGroup = await PromptGroup.create({
+        name: 'Private Access Test Group',
+        author: testUsers.owner._id,
+        authorName: testUsers.owner.name,
+        productionId: new ObjectId(),
+      });
+
+      // Create prompts in their respective groups
+      await Prompt.create({
+        prompt: 'Public prompt',
+        name: 'Public',
+        author: testUsers.owner._id,
+        groupId: publicPromptGroup._id,
+        type: 'text',
+      });
+
+      await Prompt.create({
+        prompt: 'Private prompt',
+        name: 'Private',
+        author: testUsers.owner._id,
+        groupId: privatePromptGroup._id,
+        type: 'text',
+      });
+
+      // Grant public view access to publicPromptGroup
+      await permissionService.grantPermission({
+        principalType: PrincipalType.PUBLIC,
+        principalId: null,
+        resourceType: ResourceType.PROMPTGROUP,
+        resourceId: publicPromptGroup._id,
+        accessRoleId: AccessRoleIds.PROMPTGROUP_VIEWER,
+        grantedBy: testUsers.owner._id,
+      });
+
+      // Grant only owner access to privatePromptGroup
+      await permissionService.grantPermission({
+        principalType: PrincipalType.USER,
+        principalId: testUsers.owner._id,
+        resourceType: ResourceType.PROMPTGROUP,
+        resourceId: privatePromptGroup._id,
+        accessRoleId: AccessRoleIds.PROMPTGROUP_OWNER,
+        grantedBy: testUsers.owner._id,
+      });
+    });
+
+    afterEach(async () => {
+      await Prompt.deleteMany({});
+      await PromptGroup.deleteMany({});
+      await AclEntry.deleteMany({});
+    });
+
+    it('public prompt should be accessible to any user', async () => {
+      const hasAccess = await permissionService.checkPermission({
+        userId: testUsers.noAccess._id,
+        resourceType: ResourceType.PROMPTGROUP,
+        resourceId: publicPromptGroup._id,
+        requiredPermission: PermissionBits.VIEW,
+        includePublic: true,
+      });
+
+      expect(hasAccess).toBe(true);
+    });
+
+    it('private prompt should not be accessible to unauthorized users', async () => {
+      const hasAccess = await permissionService.checkPermission({
+        userId: testUsers.noAccess._id,
+        resourceType: ResourceType.PROMPTGROUP,
+        resourceId: privatePromptGroup._id,
+        requiredPermission: PermissionBits.VIEW,
+        includePublic: true,
+      });
+
+      expect(hasAccess).toBe(false);
+    });
+  });
+
+  describe('Prompt Deletion', () => {
+    let testPromptGroup;
+
+    it('should remove ACL entries when prompt is deleted', async () => {
+      testPromptGroup = await PromptGroup.create({
+        name: 'Deletion Test Group',
+        author: testUsers.owner._id,
+        authorName: testUsers.owner.name,
+        productionId: new ObjectId(),
+      });
+
+      const prompt = await promptFns.savePrompt({
+        author: testUsers.owner._id,
+        prompt: {
+          prompt: 'To be deleted',
+          name: 'Delete Test',
+          groupId: testPromptGroup._id,
+          type: 'text',
+        },
+      });
+
+      // Check if savePrompt returned an error
+      if (!prompt || !prompt.prompt) {
+        throw new Error(`Failed to save prompt: ${prompt?.message || 'Unknown error'}`);
+      }
+
+      const testPromptId = prompt.prompt._id;
+      const promptGroupId = testPromptGroup._id;
+
+      // Grant permission
+      await permissionService.grantPermission({
+        principalType: PrincipalType.USER,
+        principalId: testUsers.owner._id,
+        resourceType: ResourceType.PROMPTGROUP,
+        resourceId: testPromptGroup._id,
+        accessRoleId: AccessRoleIds.PROMPTGROUP_OWNER,
+        grantedBy: testUsers.owner._id,
+      });
+
+      // Verify ACL entry exists
+      const beforeDelete = await AclEntry.find({
+        resourceType: ResourceType.PROMPTGROUP,
+        resourceId: testPromptGroup._id,
+      });
+      expect(beforeDelete).toHaveLength(1);
+
+      // Delete the prompt
+      await promptFns.deletePrompt({
+        promptId: testPromptId,
+        groupId: promptGroupId,
+        author: testUsers.owner._id,
+        role: SystemRoles.USER,
+      });
+
+      // Verify ACL entries are removed
+      const aclEntries = await AclEntry.find({
+        resourceType: ResourceType.PROMPTGROUP,
+        resourceId: testPromptGroup._id,
+      });
+
+      expect(aclEntries).toHaveLength(0);
+    });
+  });
+
+  describe('Backwards Compatibility', () => {
+    it('should handle prompts without ACL entries gracefully', async () => {
+      // Create a prompt group first
+      const promptGroup = await PromptGroup.create({
+        name: 'Legacy Test Group',
+        author: testUsers.owner._id,
+        authorName: testUsers.owner.name,
+        productionId: new ObjectId(),
+      });
+
+      // Create a prompt without ACL entries (legacy prompt)
+      const legacyPrompt = await Prompt.create({
+        prompt: 'Legacy prompt without ACL',
+        name: 'Legacy',
+        author: testUsers.owner._id,
+        groupId: promptGroup._id,
+        type: 'text',
+      });
+
+      // The system should handle this gracefully
+      const prompt = await promptFns.getPrompt({ _id: legacyPrompt._id });
+      expect(prompt).toBeTruthy();
+      expect(prompt._id.toString()).toBe(legacyPrompt._id.toString());
+    });
+  });
+});

api/models/PromptGroupMigration.spec.js

@@ -0,0 +1,280 @@
+const mongoose = require('mongoose');
+const { ObjectId } = require('mongodb');
+const { logger } = require('@librechat/data-schemas');
+const { MongoMemoryServer } = require('mongodb-memory-server');
+const {
+  Constants,
+  ResourceType,
+  AccessRoleIds,
+  PrincipalType,
+  PrincipalModel,
+  PermissionBits,
+} = require('librechat-data-provider');
+
+// Mock the config/connect module to prevent connection attempts during tests
+jest.mock('../../config/connect', () => jest.fn().mockResolvedValue(true));
+
+// Disable console for tests
+logger.silent = true;
+
+describe('PromptGroup Migration Script', () => {
+  let mongoServer;
+  let Prompt, PromptGroup, AclEntry, AccessRole, User, Project;
+  let migrateToPromptGroupPermissions;
+  let testOwner, testProject;
+  let ownerRole, viewerRole;
+
+  beforeAll(async () => {
+    // Set up MongoDB memory server
+    mongoServer = await MongoMemoryServer.create();
+    const mongoUri = mongoServer.getUri();
+    await mongoose.connect(mongoUri);
+
+    // Initialize models
+    const dbModels = require('~/db/models');
+    Prompt = dbModels.Prompt;
+    PromptGroup = dbModels.PromptGroup;
+    AclEntry = dbModels.AclEntry;
+    AccessRole = dbModels.AccessRole;
+    User = dbModels.User;
+    Project = dbModels.Project;
+
+    // Create test user
+    testOwner = await User.create({
+      name: 'Test Owner',
+      email: 'owner@test.com',
+      role: 'USER',
+    });
+
+    // Create test project with the proper name
+    const projectName = Constants.GLOBAL_PROJECT_NAME || 'instance';
+    testProject = await Project.create({
+      name: projectName,
+      description: 'Global project',
+      promptGroupIds: [],
+    });
+
+    // Create promptGroup access roles
+    ownerRole = await AccessRole.create({
+      accessRoleId: AccessRoleIds.PROMPTGROUP_OWNER,
+      name: 'Owner',
+      description: 'Full control over promptGroups',
+      resourceType: ResourceType.PROMPTGROUP,
+      permBits:
+        PermissionBits.VIEW | PermissionBits.EDIT | PermissionBits.DELETE | PermissionBits.SHARE,
+    });
+
+    viewerRole = await AccessRole.create({
+      accessRoleId: AccessRoleIds.PROMPTGROUP_VIEWER,
+      name: 'Viewer',
+      description: 'Can view promptGroups',
+      resourceType: ResourceType.PROMPTGROUP,
+      permBits: PermissionBits.VIEW,
+    });
+
+    await AccessRole.create({
+      accessRoleId: AccessRoleIds.PROMPTGROUP_EDITOR,
+      name: 'Editor',
+      description: 'Can view and edit promptGroups',
+      resourceType: ResourceType.PROMPTGROUP,
+      permBits: PermissionBits.VIEW | PermissionBits.EDIT,
+    });
+
+    // Import migration function
+    const migration = require('../../config/migrate-prompt-permissions');
+    migrateToPromptGroupPermissions = migration.migrateToPromptGroupPermissions;
+  });
+
+  afterAll(async () => {
+    await mongoose.disconnect();
+    await mongoServer.stop();
+  });
+
+  beforeEach(async () => {
+    // Clean up before each test
+    await Prompt.deleteMany({});
+    await PromptGroup.deleteMany({});
+    await AclEntry.deleteMany({});
+    // Reset the project's promptGroupIds array
+    testProject.promptGroupIds = [];
+    await testProject.save();
+  });
+
+  it('should categorize promptGroups correctly in dry run', async () => {
+    // Create global prompt group (in Global project)
+    const globalPromptGroup = await PromptGroup.create({
+      name: 'Global Group',
+      author: testOwner._id,
+      authorName: testOwner.name,
+      productionId: new ObjectId(),
+    });
+
+    // Create private prompt group (not in any project)
+    await PromptGroup.create({
+      name: 'Private Group',
+      author: testOwner._id,
+      authorName: testOwner.name,
+      productionId: new ObjectId(),
+    });
+
+    // Add global group to project's promptGroupIds array
+    testProject.promptGroupIds = [globalPromptGroup._id];
+    await testProject.save();
+
+    const result = await migrateToPromptGroupPermissions({ dryRun: true });
+
+    expect(result.dryRun).toBe(true);
+    expect(result.summary.total).toBe(2);
+    expect(result.summary.globalViewAccess).toBe(1);
+    expect(result.summary.privateGroups).toBe(1);
+  });
+
+  it('should grant appropriate permissions during migration', async () => {
+    // Create prompt groups
+    const globalPromptGroup = await PromptGroup.create({
+      name: 'Global Group',
+      author: testOwner._id,
+      authorName: testOwner.name,
+      productionId: new ObjectId(),
+    });
+
+    const privatePromptGroup = await PromptGroup.create({
+      name: 'Private Group',
+      author: testOwner._id,
+      authorName: testOwner.name,
+      productionId: new ObjectId(),
+    });
+
+    // Add global group to project's promptGroupIds array
+    testProject.promptGroupIds = [globalPromptGroup._id];
+    await testProject.save();
+
+    const result = await migrateToPromptGroupPermissions({ dryRun: false });
+
+    expect(result.migrated).toBe(2);
+    expect(result.errors).toBe(0);
+    expect(result.ownerGrants).toBe(2);
+    expect(result.publicViewGrants).toBe(1);
+
+    // Check global promptGroup permissions
+    const globalOwnerEntry = await AclEntry.findOne({
+      resourceType: ResourceType.PROMPTGROUP,
+      resourceId: globalPromptGroup._id,
+      principalType: PrincipalType.USER,
+      principalId: testOwner._id,
+    });
+    expect(globalOwnerEntry).toBeTruthy();
+    expect(globalOwnerEntry.permBits).toBe(ownerRole.permBits);
+
+    const globalPublicEntry = await AclEntry.findOne({
+      resourceType: ResourceType.PROMPTGROUP,
+      resourceId: globalPromptGroup._id,
+      principalType: PrincipalType.PUBLIC,
+    });
+    expect(globalPublicEntry).toBeTruthy();
+    expect(globalPublicEntry.permBits).toBe(viewerRole.permBits);
+
+    // Check private promptGroup permissions
+    const privateOwnerEntry = await AclEntry.findOne({
+      resourceType: ResourceType.PROMPTGROUP,
+      resourceId: privatePromptGroup._id,
+      principalType: PrincipalType.USER,
+      principalId: testOwner._id,
+    });
+    expect(privateOwnerEntry).toBeTruthy();
+    expect(privateOwnerEntry.permBits).toBe(ownerRole.permBits);
+
+    const privatePublicEntry = await AclEntry.findOne({
+      resourceType: ResourceType.PROMPTGROUP,
+      resourceId: privatePromptGroup._id,
+      principalType: PrincipalType.PUBLIC,
+    });
+    expect(privatePublicEntry).toBeNull();
+  });
+
+  it('should skip promptGroups that already have ACL entries', async () => {
+    // Create prompt groups
+    const promptGroup1 = await PromptGroup.create({
+      name: 'Group 1',
+      author: testOwner._id,
+      authorName: testOwner.name,
+      productionId: new ObjectId(),
+    });
+
+    const promptGroup2 = await PromptGroup.create({
+      name: 'Group 2',
+      author: testOwner._id,
+      authorName: testOwner.name,
+      productionId: new ObjectId(),
+    });
+
+    // Grant permission to one promptGroup manually (simulating it already has ACL)
+    await AclEntry.create({
+      principalType: PrincipalType.USER,
+      principalId: testOwner._id,
+      principalModel: PrincipalModel.USER,
+      resourceType: ResourceType.PROMPTGROUP,
+      resourceId: promptGroup1._id,
+      permBits: ownerRole.permBits,
+      roleId: ownerRole._id,
+      grantedBy: testOwner._id,
+      grantedAt: new Date(),
+    });
+
+    const result = await migrateToPromptGroupPermissions({ dryRun: false });
+
+    // Should only migrate promptGroup2, skip promptGroup1
+    expect(result.migrated).toBe(1);
+    expect(result.errors).toBe(0);
+
+    // Verify promptGroup2 now has permissions
+    const group2Entry = await AclEntry.findOne({
+      resourceType: ResourceType.PROMPTGROUP,
+      resourceId: promptGroup2._id,
+    });
+    expect(group2Entry).toBeTruthy();
+  });
+
+  it('should handle promptGroups with prompts correctly', async () => {
+    // Create a promptGroup with some prompts
+    const promptGroup = await PromptGroup.create({
+      name: 'Group with Prompts',
+      author: testOwner._id,
+      authorName: testOwner.name,
+      productionId: new ObjectId(),
+    });
+
+    // Create some prompts in this group
+    await Prompt.create({
+      prompt: 'First prompt',
+      author: testOwner._id,
+      groupId: promptGroup._id,
+      type: 'text',
+    });
+
+    await Prompt.create({
+      prompt: 'Second prompt',
+      author: testOwner._id,
+      groupId: promptGroup._id,
+      type: 'text',
+    });
+
+    const result = await migrateToPromptGroupPermissions({ dryRun: false });
+
+    expect(result.migrated).toBe(1);
+    expect(result.errors).toBe(0);
+
+    // Verify the promptGroup has permissions
+    const groupEntry = await AclEntry.findOne({
+      resourceType: ResourceType.PROMPTGROUP,
+      resourceId: promptGroup._id,
+    });
+    expect(groupEntry).toBeTruthy();
+
+    // Verify no prompt-level permissions were created
+    const promptEntries = await AclEntry.find({
+      resourceType: 'prompt',
+    });
+    expect(promptEntries).toHaveLength(0);
+  });
+});

api/models/Role.js

@@ -2,7 +2,6 @@ const {
   CacheKeys,
   SystemRoles,
   roleDefaults,
-  PermissionTypes,
   permissionsSchema,
   removeNullishValues,
 } = require('librechat-data-provider');
@@ -17,7 +16,7 @@ const { Role } = require('~/db/models');
  *
  * @param {string} roleName - The name of the role to find or create.
  * @param {string|string[]} [fieldsToSelect] - The fields to include or exclude in the returned document.
- * @returns {Promise<Object>} A plain object representing the role document.
+ * @returns {Promise<IRole>} Role document.
  */
 const getRoleByName = async function (roleName, fieldsToSelect = null) {
   const cache = getLogStores(CacheKeys.ROLES);
@@ -73,8 +72,9 @@ const updateRoleByName = async function (roleName, updates) {
  * Updates access permissions for a specific role and multiple permission types.
  * @param {string} roleName - The role to update.
  * @param {Object.<PermissionTypes, Object.<Permissions, boolean>>} permissionsUpdate - Permissions to update and their values.
+ * @param {IRole} [roleData] - Optional role data to use instead of fetching from the database.
  */
-async function updateAccessPermissions(roleName, permissionsUpdate) {
+async function updateAccessPermissions(roleName, permissionsUpdate, roleData) {
   // Filter and clean the permission updates based on our schema definition.
   const updates = {};
   for (const [permissionType, permissions] of Object.entries(permissionsUpdate)) {
@@ -87,7 +87,7 @@ async function updateAccessPermissions(roleName, permissionsUpdate) {
   }
 
   try {
-    const role = await getRoleByName(roleName);
+    const role = roleData ?? (await getRoleByName(roleName));
     if (!role) {
       return;
     }
@@ -114,7 +114,6 @@ async function updateAccessPermissions(roleName, permissionsUpdate) {
       }
     }
 
-    // Process the current updates
     for (const [permissionType, permissions] of Object.entries(updates)) {
       const currentTypePermissions = currentPermissions[permissionType] || {};
       updatedPermissions[permissionType] = { ...currentTypePermissions };

api/models/Transaction.js

@@ -1,5 +1,4 @@
 const { logger } = require('@librechat/data-schemas');
-const { getBalanceConfig } = require('~/server/services/Config');
 const { getMultiplier, getCacheMultiplier } = require('./tx');
 const { Transaction, Balance } = require('~/db/models');
 
@@ -187,20 +186,23 @@ async function createAutoRefillTransaction(txData) {
 
 /**
  * Static method to create a transaction and update the balance
- * @param {txData} txData - Transaction data.
+ * @param {txData} _txData - Transaction data.
  */
-async function createTransaction(txData) {
+async function createTransaction(_txData) {
+  const { balance, transactions, ...txData } = _txData;
   if (txData.rawAmount != null && isNaN(txData.rawAmount)) {
     return;
   }
 
+  if (transactions?.enabled === false) {
+    return;
+  }
+
   const transaction = new Transaction(txData);
   transaction.endpointTokenConfig = txData.endpointTokenConfig;
   calculateTokenValue(transaction);
 
   await transaction.save();
-
-  const balance = await getBalanceConfig();
   if (!balance?.enabled) {
     return;
   }
@@ -221,9 +223,14 @@ async function createTransaction(txData) {
 
 /**
  * Static method to create a structured transaction and update the balance
- * @param {txData} txData - Transaction data.
+ * @param {txData} _txData - Transaction data.
  */
-async function createStructuredTransaction(txData) {
+async function createStructuredTransaction(_txData) {
+  const { balance, transactions, ...txData } = _txData;
+  if (transactions?.enabled === false) {
+    return;
+  }
+
   const transaction = new Transaction({
     ...txData,
     endpointTokenConfig: txData.endpointTokenConfig,
@@ -233,7 +240,6 @@ async function createStructuredTransaction(txData) {
 
   await transaction.save();
 
-  const balance = await getBalanceConfig();
   if (!balance?.enabled) {
     return;
   }

api/models/Transaction.spec.js

@@ -1,13 +1,9 @@
 const mongoose = require('mongoose');
 const { MongoMemoryServer } = require('mongodb-memory-server');
 const { spendTokens, spendStructuredTokens } = require('./spendTokens');
-const { getBalanceConfig } = require('~/server/services/Config');
 const { getMultiplier, getCacheMultiplier } = require('./tx');
-const { createTransaction } = require('./Transaction');
-const { Balance } = require('~/db/models');
-
-// Mock the custom config module so we can control the balance flag.
-jest.mock('~/server/services/Config');
+const { createTransaction, createStructuredTransaction } = require('./Transaction');
+const { Balance, Transaction } = require('~/db/models');
 
 let mongoServer;
 beforeAll(async () => {
@@ -23,8 +19,6 @@ afterAll(async () => {
 
 beforeEach(async () => {
   await mongoose.connection.dropDatabase();
-  // Default: enable balance updates in tests.
-  getBalanceConfig.mockResolvedValue({ enabled: true });
 });
 
 describe('Regular Token Spending Tests', () => {
@@ -41,6 +35,7 @@ describe('Regular Token Spending Tests', () => {
       model,
       context: 'test',
       endpointTokenConfig: null,
+      balance: { enabled: true },
     };
 
     const tokenUsage = {
@@ -74,6 +69,7 @@ describe('Regular Token Spending Tests', () => {
       model,
       context: 'test',
       endpointTokenConfig: null,
+      balance: { enabled: true },
     };
 
     const tokenUsage = {
@@ -104,6 +100,7 @@ describe('Regular Token Spending Tests', () => {
       model,
       context: 'test',
       endpointTokenConfig: null,
+      balance: { enabled: true },
     };
 
     const tokenUsage = {};
@@ -128,6 +125,7 @@ describe('Regular Token Spending Tests', () => {
       model,
       context: 'test',
       endpointTokenConfig: null,
+      balance: { enabled: true },
     };
 
     const tokenUsage = { promptTokens: 100 };
@@ -143,8 +141,7 @@ describe('Regular Token Spending Tests', () => {
   });
 
   test('spendTokens should not update balance when balance feature is disabled', async () => {
-    // Arrange: Override the config to disable balance updates.
-    getBalanceConfig.mockResolvedValue({ balance: { enabled: false } });
+    // Arrange: Balance config is now passed directly in txData
     const userId = new mongoose.Types.ObjectId();
     const initialBalance = 10000000;
     await Balance.create({ user: userId, tokenCredits: initialBalance });
@@ -156,6 +153,7 @@ describe('Regular Token Spending Tests', () => {
       model,
       context: 'test',
       endpointTokenConfig: null,
+      balance: { enabled: false },
     };
 
     const tokenUsage = {
@@ -186,6 +184,7 @@ describe('Structured Token Spending Tests', () => {
       model,
       context: 'message',
       endpointTokenConfig: null,
+      balance: { enabled: true },
     };
 
     const tokenUsage = {
@@ -239,6 +238,7 @@ describe('Structured Token Spending Tests', () => {
       conversationId: 'test-convo',
       model,
       context: 'message',
+      balance: { enabled: true },
     };
 
     const tokenUsage = {
@@ -271,6 +271,7 @@ describe('Structured Token Spending Tests', () => {
       conversationId: 'test-convo',
       model,
       context: 'message',
+      balance: { enabled: true },
     };
 
     const tokenUsage = {
@@ -302,6 +303,7 @@ describe('Structured Token Spending Tests', () => {
       conversationId: 'test-convo',
       model,
       context: 'message',
+      balance: { enabled: true },
     };
 
     const tokenUsage = {};
@@ -328,6 +330,7 @@ describe('Structured Token Spending Tests', () => {
       conversationId: 'test-convo',
       model,
       context: 'incomplete',
+      balance: { enabled: true },
     };
 
     const tokenUsage = {
@@ -364,6 +367,7 @@ describe('NaN Handling Tests', () => {
       endpointTokenConfig: null,
       rawAmount: NaN,
       tokenType: 'prompt',
+      balance: { enabled: true },
     };
 
     // Act
@@ -375,3 +379,188 @@ describe('NaN Handling Tests', () => {
     expect(balance.tokenCredits).toBe(initialBalance);
   });
 });
+
+describe('Transactions Config Tests', () => {
+  test('createTransaction should not save when transactions.enabled is false', async () => {
+    // Arrange
+    const userId = new mongoose.Types.ObjectId();
+    const initialBalance = 10000000;
+    await Balance.create({ user: userId, tokenCredits: initialBalance });
+
+    const model = 'gpt-3.5-turbo';
+    const txData = {
+      user: userId,
+      conversationId: 'test-conversation-id',
+      model,
+      context: 'test',
+      endpointTokenConfig: null,
+      rawAmount: -100,
+      tokenType: 'prompt',
+      transactions: { enabled: false },
+    };
+
+    // Act
+    const result = await createTransaction(txData);
+
+    // Assert: No transaction should be created
+    expect(result).toBeUndefined();
+    const transactions = await Transaction.find({ user: userId });
+    expect(transactions).toHaveLength(0);
+    const balance = await Balance.findOne({ user: userId });
+    expect(balance.tokenCredits).toBe(initialBalance);
+  });
+
+  test('createTransaction should save when transactions.enabled is true', async () => {
+    // Arrange
+    const userId = new mongoose.Types.ObjectId();
+    const initialBalance = 10000000;
+    await Balance.create({ user: userId, tokenCredits: initialBalance });
+
+    const model = 'gpt-3.5-turbo';
+    const txData = {
+      user: userId,
+      conversationId: 'test-conversation-id',
+      model,
+      context: 'test',
+      endpointTokenConfig: null,
+      rawAmount: -100,
+      tokenType: 'prompt',
+      transactions: { enabled: true },
+      balance: { enabled: true },
+    };
+
+    // Act
+    const result = await createTransaction(txData);
+
+    // Assert: Transaction should be created
+    expect(result).toBeDefined();
+    expect(result.balance).toBeLessThan(initialBalance);
+    const transactions = await Transaction.find({ user: userId });
+    expect(transactions).toHaveLength(1);
+    expect(transactions[0].rawAmount).toBe(-100);
+  });
+
+  test('createTransaction should save when balance.enabled is true even if transactions config is missing', async () => {
+    // Arrange
+    const userId = new mongoose.Types.ObjectId();
+    const initialBalance = 10000000;
+    await Balance.create({ user: userId, tokenCredits: initialBalance });
+
+    const model = 'gpt-3.5-turbo';
+    const txData = {
+      user: userId,
+      conversationId: 'test-conversation-id',
+      model,
+      context: 'test',
+      endpointTokenConfig: null,
+      rawAmount: -100,
+      tokenType: 'prompt',
+      balance: { enabled: true },
+      // No transactions config provided
+    };
+
+    // Act
+    const result = await createTransaction(txData);
+
+    // Assert: Transaction should be created (backward compatibility)
+    expect(result).toBeDefined();
+    expect(result.balance).toBeLessThan(initialBalance);
+    const transactions = await Transaction.find({ user: userId });
+    expect(transactions).toHaveLength(1);
+  });
+
+  test('createTransaction should save transaction but not update balance when balance is disabled but transactions enabled', async () => {
+    // Arrange
+    const userId = new mongoose.Types.ObjectId();
+    const initialBalance = 10000000;
+    await Balance.create({ user: userId, tokenCredits: initialBalance });
+
+    const model = 'gpt-3.5-turbo';
+    const txData = {
+      user: userId,
+      conversationId: 'test-conversation-id',
+      model,
+      context: 'test',
+      endpointTokenConfig: null,
+      rawAmount: -100,
+      tokenType: 'prompt',
+      transactions: { enabled: true },
+      balance: { enabled: false },
+    };
+
+    // Act
+    const result = await createTransaction(txData);
+
+    // Assert: Transaction should be created but balance unchanged
+    expect(result).toBeUndefined();
+    const transactions = await Transaction.find({ user: userId });
+    expect(transactions).toHaveLength(1);
+    expect(transactions[0].rawAmount).toBe(-100);
+    const balance = await Balance.findOne({ user: userId });
+    expect(balance.tokenCredits).toBe(initialBalance);
+  });
+
+  test('createStructuredTransaction should not save when transactions.enabled is false', async () => {
+    // Arrange
+    const userId = new mongoose.Types.ObjectId();
+    const initialBalance = 10000000;
+    await Balance.create({ user: userId, tokenCredits: initialBalance });
+
+    const model = 'claude-3-5-sonnet';
+    const txData = {
+      user: userId,
+      conversationId: 'test-conversation-id',
+      model,
+      context: 'message',
+      tokenType: 'prompt',
+      inputTokens: -10,
+      writeTokens: -100,
+      readTokens: -5,
+      transactions: { enabled: false },
+    };
+
+    // Act
+    const result = await createStructuredTransaction(txData);
+
+    // Assert: No transaction should be created
+    expect(result).toBeUndefined();
+    const transactions = await Transaction.find({ user: userId });
+    expect(transactions).toHaveLength(0);
+    const balance = await Balance.findOne({ user: userId });
+    expect(balance.tokenCredits).toBe(initialBalance);
+  });
+
+  test('createStructuredTransaction should save transaction but not update balance when balance is disabled but transactions enabled', async () => {
+    // Arrange
+    const userId = new mongoose.Types.ObjectId();
+    const initialBalance = 10000000;
+    await Balance.create({ user: userId, tokenCredits: initialBalance });
+
+    const model = 'claude-3-5-sonnet';
+    const txData = {
+      user: userId,
+      conversationId: 'test-conversation-id',
+      model,
+      context: 'message',
+      tokenType: 'prompt',
+      inputTokens: -10,
+      writeTokens: -100,
+      readTokens: -5,
+      transactions: { enabled: true },
+      balance: { enabled: false },
+    };
+
+    // Act
+    const result = await createStructuredTransaction(txData);
+
+    // Assert: Transaction should be created but balance unchanged
+    expect(result).toBeUndefined();
+    const transactions = await Transaction.find({ user: userId });
+    expect(transactions).toHaveLength(1);
+    expect(transactions[0].inputTokens).toBe(-10);
+    expect(transactions[0].writeTokens).toBe(-100);
+    expect(transactions[0].readTokens).toBe(-5);
+    const balance = await Balance.findOne({ user: userId });
+    expect(balance.tokenCredits).toBe(initialBalance);
+  });
+});

api/models/balanceMethods.js

@@ -118,7 +118,7 @@ const addIntervalToDate = (date, value, unit) => {
  * @async
  * @function
  * @param {Object} params - The function parameters.
- * @param {Express.Request} params.req - The Express request object.
+ * @param {ServerRequest} params.req - The Express request object.
  * @param {Express.Response} params.res - The Express response object.
  * @param {Object} params.txData - The transaction data.
  * @param {string} params.txData.user - The user ID or identifier.

api/models/convoStructure.spec.js

@@ -1,47 +1,9 @@
 const mongoose = require('mongoose');
+const { buildTree } = require('librechat-data-provider');
 const { MongoMemoryServer } = require('mongodb-memory-server');
 const { getMessages, bulkSaveMessages } = require('./Message');
 const { Message } = require('~/db/models');
 
-// Original version of buildTree function
-function buildTree({ messages, fileMap }) {
-  if (messages === null) {
-    return null;
-  }
-
-  const messageMap = {};
-  const rootMessages = [];
-  const childrenCount = {};
-
-  messages.forEach((message) => {
-    const parentId = message.parentMessageId ?? '';
-    childrenCount[parentId] = (childrenCount[parentId] || 0) + 1;
-
-    const extendedMessage = {
-      ...message,
-      children: [],
-      depth: 0,
-      siblingIndex: childrenCount[parentId] - 1,
-    };
-
-    if (message.files && fileMap) {
-      extendedMessage.files = message.files.map((file) => fileMap[file.file_id ?? ''] ?? file);
-    }
-
-    messageMap[message.messageId] = extendedMessage;
-
-    const parentMessage = messageMap[parentId];
-    if (parentMessage) {
-      parentMessage.children.push(extendedMessage);
-      extendedMessage.depth = parentMessage.depth + 1;
-    } else {
-      rootMessages.push(extendedMessage);
-    }
-  });
-
-  return rootMessages;
-}
-
 let mongod;
 beforeAll(async () => {
   mongod = await MongoMemoryServer.create();

api/models/index.js

@@ -22,9 +22,17 @@ const {
 } = require('./Message');
 const { getConvoTitle, getConvo, saveConvo, deleteConvos } = require('./Conversation');
 const { getPreset, getPresets, savePreset, deletePresets } = require('./Preset');
+const { File } = require('~/db/models');
+
+const seedDatabase = async () => {
+  await methods.initializeRoles();
+  await methods.seedDefaultRoles();
+  await methods.ensureDefaultCategories();
+};
 
 module.exports = {
   ...methods,
+  seedDatabase,
   comparePassword,
   findFileById,
   createFile,
@@ -51,4 +59,6 @@ module.exports = {
   getPresets,
   savePreset,
   deletePresets,
+
+  Files: File,
 };

api/models/interface.js

@@ -0,0 +1,24 @@
+const { logger } = require('@librechat/data-schemas');
+const { updateInterfacePermissions: updateInterfacePerms } = require('@librechat/api');
+const { getRoleByName, updateAccessPermissions } = require('./Role');
+
+/**
+ * Update interface permissions based on app configuration.
+ * Must be done independently from loading the app config.
+ * @param {AppConfig} appConfig
+ */
+async function updateInterfacePermissions(appConfig) {
+  try {
+    await updateInterfacePerms({
+      appConfig,
+      getRoleByName,
+      updateAccessPermissions,
+    });
+  } catch (error) {
+    logger.error('Error updating interface permissions:', error);
+  }
+}
+
+module.exports = {
+  updateInterfacePermissions,
+};

api/models/spendTokens.js

@@ -1,17 +1,11 @@
-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.
  *
  * @function
  * @async
- * @param {Object} txData - Transaction data.
- * @param {mongoose.Schema.Types.ObjectId} txData.user - The user ID.
- * @param {String} txData.conversationId - The ID of the conversation.
- * @param {String} txData.model - The model name.
- * @param {String} txData.context - The context in which the transaction is made.
- * @param {EndpointTokenConfig} [txData.endpointTokenConfig] - The current endpoint token config.
- * @param {String} [txData.valueKey] - The value key (optional).
+ * @param {txData} txData - Transaction data.
  * @param {Object} tokenUsage - The number of tokens used.
  * @param {Number} tokenUsage.promptTokens - The number of prompt tokens used.
  * @param {Number} tokenUsage.completionTokens - The number of completion tokens used.
@@ -69,13 +63,7 @@ const spendTokens = async (txData, tokenUsage) => {
  *
  * @function
  * @async
- * @param {Object} txData - Transaction data.
- * @param {mongoose.Schema.Types.ObjectId} txData.user - The user ID.
- * @param {String} txData.conversationId - The ID of the conversation.
- * @param {String} txData.model - The model name.
- * @param {String} txData.context - The context in which the transaction is made.
- * @param {EndpointTokenConfig} [txData.endpointTokenConfig] - The current endpoint token config.
- * @param {String} [txData.valueKey] - The value key (optional).
+ * @param {txData} txData - Transaction data.
  * @param {Object} tokenUsage - The number of tokens used.
  * @param {Object} tokenUsage.promptTokens - The number of prompt tokens used.
  * @param {Number} tokenUsage.promptTokens.input - The number of input tokens.

api/models/spendTokens.spec.js

@@ -5,7 +5,6 @@ const { createTransaction, createAutoRefillTransaction } = require('./Transactio
 
 require('~/db/models');
 
-// Mock the logger to prevent console output during tests
 jest.mock('~/config', () => ({
   logger: {
     debug: jest.fn(),
@@ -13,10 +12,6 @@ jest.mock('~/config', () => ({
   },
 }));
 
-// Mock the Config service
-const { getBalanceConfig } = require('~/server/services/Config');
-jest.mock('~/server/services/Config');
-
 describe('spendTokens', () => {
   let mongoServer;
   let userId;
@@ -44,8 +39,7 @@ describe('spendTokens', () => {
     // Create a new user ID for each test
     userId = new mongoose.Types.ObjectId();
 
-    // Mock the balance config to be enabled by default
-    getBalanceConfig.mockResolvedValue({ enabled: true });
+    // Balance config is now passed directly in txData
   });
 
   it('should create transactions for both prompt and completion tokens', async () => {
@@ -60,6 +54,7 @@ describe('spendTokens', () => {
       conversationId: 'test-convo',
       model: 'gpt-3.5-turbo',
       context: 'test',
+      balance: { enabled: true },
     };
     const tokenUsage = {
       promptTokens: 100,
@@ -98,6 +93,7 @@ describe('spendTokens', () => {
       conversationId: 'test-convo',
       model: 'gpt-3.5-turbo',
       context: 'test',
+      balance: { enabled: true },
     };
     const tokenUsage = {
       promptTokens: 100,
@@ -127,6 +123,7 @@ describe('spendTokens', () => {
       conversationId: 'test-convo',
       model: 'gpt-3.5-turbo',
       context: 'test',
+      balance: { enabled: true },
     };
     const tokenUsage = {};
 
@@ -138,8 +135,7 @@ describe('spendTokens', () => {
   });
 
   it('should not update balance when the balance feature is disabled', async () => {
-    // Override configuration: disable balance updates
-    getBalanceConfig.mockResolvedValue({ enabled: false });
+    // Balance is now passed directly in txData
     // Create a balance for the user
     await Balance.create({
       user: userId,
@@ -151,6 +147,7 @@ describe('spendTokens', () => {
       conversationId: 'test-convo',
       model: 'gpt-3.5-turbo',
       context: 'test',
+      balance: { enabled: false },
     };
     const tokenUsage = {
       promptTokens: 100,
@@ -180,6 +177,7 @@ describe('spendTokens', () => {
       conversationId: 'test-convo',
       model: 'gpt-4', // Using a more expensive model
       context: 'test',
+      balance: { enabled: true },
     };
 
     // Spending more tokens than the user has balance for
@@ -233,6 +231,7 @@ describe('spendTokens', () => {
       conversationId: 'test-convo-1',
       model: 'gpt-4',
       context: 'test',
+      balance: { enabled: true },
     };
 
     const tokenUsage1 = {
@@ -252,6 +251,7 @@ describe('spendTokens', () => {
       conversationId: 'test-convo-2',
       model: 'gpt-4',
       context: 'test',
+      balance: { enabled: true },
     };
 
     const tokenUsage2 = {
@@ -292,6 +292,7 @@ describe('spendTokens', () => {
       tokenType: 'completion',
       rawAmount: -100,
       context: 'test',
+      balance: { enabled: true },
     });
 
     console.log('Direct Transaction.create result:', directResult);
@@ -316,6 +317,7 @@ describe('spendTokens', () => {
         conversationId: `test-convo-${model}`,
         model,
         context: 'test',
+        balance: { enabled: true },
       };
 
       const tokenUsage = {
@@ -352,6 +354,7 @@ describe('spendTokens', () => {
       conversationId: 'test-convo-1',
       model: 'claude-3-5-sonnet',
       context: 'test',
+      balance: { enabled: true },
     };
 
     const tokenUsage1 = {
@@ -375,6 +378,7 @@ describe('spendTokens', () => {
       conversationId: 'test-convo-2',
       model: 'claude-3-5-sonnet',
       context: 'test',
+      balance: { enabled: true },
     };
 
     const tokenUsage2 = {
@@ -426,6 +430,7 @@ describe('spendTokens', () => {
       conversationId: 'test-convo',
       model: 'claude-3-5-sonnet', // Using a model that supports structured tokens
       context: 'test',
+      balance: { enabled: true },
     };
 
     // Spending more tokens than the user has balance for
@@ -505,6 +510,7 @@ describe('spendTokens', () => {
         conversationId,
         user: userId,
         model: usage.model,
+        balance: { enabled: true },
       };
 
       // Calculate expected spend for this transaction
@@ -617,6 +623,7 @@ describe('spendTokens', () => {
           tokenType: 'credits',
           context: 'concurrent-refill-test',
           rawAmount: refillAmount,
+          balance: { enabled: true },
         }),
       );
     }
@@ -683,6 +690,7 @@ describe('spendTokens', () => {
       conversationId: 'test-convo',
       model: 'claude-3-5-sonnet',
       context: 'test',
+      balance: { enabled: true },
     };
     const tokenUsage = {
       promptTokens: {

api/models/tx.js

@@ -1,4 +1,4 @@
-const { matchModelName } = require('../utils');
+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 },
 };
 
@@ -71,81 +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-4o': { prompt: 2.5, completion: 10 },
     'gpt-4o-2024-05-13': { prompt: 5, completion: 15 },
-    'gpt-4-1106': { prompt: 10, completion: 30 },
-    'gpt-3.5-turbo-0125': { prompt: 0.5, completion: 1.5 },
-    'claude-3-opus': { prompt: 15, completion: 75 },
+    'gpt-4o-mini': { prompt: 0.15, completion: 0.6 },
+    'gpt-5': { prompt: 1.25, completion: 10 },
+    'gpt-5-nano': { prompt: 0.05, completion: 0.4 },
+    'gpt-5-mini': { prompt: 0.25, completion: 2 },
+    'gpt-5-pro': { prompt: 15, completion: 120 },
+    o1: { prompt: 15, completion: 60 },
+    'o1-mini': { prompt: 1.1, completion: 4.4 },
+    'o1-preview': { prompt: 15, completion: 60 },
+    o3: { prompt: 2, completion: 8 },
+    'o3-mini': { prompt: 1.1, completion: 4.4 },
+    'o4-mini': { prompt: 1.1, completion: 4.4 },
+    'claude-instant': { prompt: 0.8, completion: 2.4 },
+    'claude-2': { prompt: 8, completion: 24 },
+    'claude-2.1': { prompt: 8, completion: 24 },
+    'claude-3-haiku': { prompt: 0.25, completion: 1.25 },
     'claude-3-sonnet': { prompt: 3, completion: 15 },
+    'claude-3-opus': { prompt: 15, completion: 75 },
+    'claude-3-5-haiku': { prompt: 0.8, completion: 4 },
+    'claude-3.5-haiku': { prompt: 0.8, completion: 4 },
     'claude-3-5-sonnet': { prompt: 3, completion: 15 },
     'claude-3.5-sonnet': { prompt: 3, completion: 15 },
     'claude-3-7-sonnet': { prompt: 3, completion: 15 },
     'claude-3.7-sonnet': { prompt: 3, completion: 15 },
-    'claude-3-5-haiku': { prompt: 0.8, completion: 4 },
-    'claude-3.5-haiku': { prompt: 0.8, completion: 4 },
-    'claude-3-haiku': { prompt: 0.25, completion: 1.25 },
-    'claude-sonnet-4': { prompt: 3, completion: 15 },
+    'claude-haiku-4-5': { prompt: 1, completion: 5 },
     'claude-opus-4': { prompt: 15, completion: 75 },
-    'claude-2.1': { prompt: 8, completion: 24 },
-    'claude-2': { prompt: 8, completion: 24 },
-    'claude-instant': { prompt: 0.8, completion: 2.4 },
-    'claude-': { prompt: 0.8, completion: 2.4 },
-    'command-r-plus': { prompt: 3, completion: 15 },
+    'claude-sonnet-4': { prompt: 3, completion: 15 },
     'command-r': { prompt: 0.5, completion: 1.5 },
-    'deepseek-reasoner': { prompt: 0.55, completion: 2.19 },
-    deepseek: { prompt: 0.14, completion: 0.28 },
-    /* cohere doesn't have rates for the older command models,
-  so this was from https://artificialanalysis.ai/models/command-light/providers */
-    command: { prompt: 0.38, completion: 0.38 },
-    gemma: { prompt: 0, completion: 0 }, // https://ai.google.dev/pricing
-    'gemma-2': { prompt: 0, completion: 0 }, // https://ai.google.dev/pricing
-    'gemma-3': { prompt: 0, completion: 0 }, // https://ai.google.dev/pricing
-    'gemma-3-27b': { prompt: 0, completion: 0 }, // https://ai.google.dev/pricing
-    'gemini-2.0-flash-lite': { prompt: 0.075, completion: 0.3 },
-    'gemini-2.0-flash': { prompt: 0.1, completion: 0.4 },
-    'gemini-2.0': { prompt: 0, completion: 0 }, // https://ai.google.dev/pricing
-    'gemini-2.5-pro': { prompt: 1.25, completion: 10 },
-    'gemini-2.5-flash': { prompt: 0.15, completion: 3.5 },
-    'gemini-2.5': { prompt: 0, completion: 0 }, // Free for a period of time
-    'gemini-1.5-flash-8b': { prompt: 0.075, completion: 0.3 },
-    'gemini-1.5-flash': { prompt: 0.15, completion: 0.6 },
+    'command-r-plus': { prompt: 3, completion: 15 },
+    'command-text': { prompt: 1.5, completion: 2.0 },
+    'deepseek-reasoner': { prompt: 0.28, completion: 0.42 },
+    'deepseek-r1': { prompt: 0.4, completion: 2.0 },
+    'deepseek-v3': { prompt: 0.2, completion: 0.8 },
+    'gemma-2': { prompt: 0.01, completion: 0.03 }, // Base pattern (using gemma-2-9b pricing)
+    'gemma-3': { prompt: 0.02, completion: 0.04 }, // Base pattern (using gemma-3n-e4b pricing)
+    'gemma-3-27b': { prompt: 0.09, completion: 0.16 },
     'gemini-1.5': { prompt: 2.5, completion: 10 },
+    'gemini-1.5-flash': { prompt: 0.15, completion: 0.6 },
+    'gemini-1.5-flash-8b': { prompt: 0.075, completion: 0.3 },
+    'gemini-2.0': { prompt: 0.1, completion: 0.4 }, // Base pattern (using 2.0-flash pricing)
+    'gemini-2.0-flash': { prompt: 0.1, completion: 0.4 },
+    'gemini-2.0-flash-lite': { prompt: 0.075, completion: 0.3 },
+    'gemini-2.5': { prompt: 0.3, completion: 2.5 }, // Base pattern (using 2.5-flash pricing)
+    'gemini-2.5-flash': { prompt: 0.3, completion: 2.5 },
+    'gemini-2.5-flash-lite': { prompt: 0.1, completion: 0.4 },
+    'gemini-2.5-pro': { prompt: 1.25, completion: 10 },
     'gemini-pro-vision': { prompt: 0.5, completion: 1.5 },
-    gemini: { prompt: 0.5, completion: 1.5 },
-    'grok-2-vision-1212': { prompt: 2.0, completion: 10.0 },
-    'grok-2-vision-latest': { prompt: 2.0, completion: 10.0 },
-    'grok-2-vision': { prompt: 2.0, completion: 10.0 },
+    grok: { prompt: 2.0, completion: 10.0 }, // Base pattern defaults to grok-2
+    'grok-beta': { prompt: 5.0, completion: 15.0 },
     'grok-vision-beta': { prompt: 5.0, completion: 15.0 },
+    'grok-2': { prompt: 2.0, completion: 10.0 },
     'grok-2-1212': { prompt: 2.0, completion: 10.0 },
     'grok-2-latest': { prompt: 2.0, completion: 10.0 },
-    'grok-2': { prompt: 2.0, completion: 10.0 },
-    'grok-3-mini-fast': { prompt: 0.4, 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-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 },
+    '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 },
     codestral: { prompt: 0.3, completion: 0.9 },
-    'ministral-8b': { prompt: 0.1, completion: 0.1 },
     'ministral-3b': { prompt: 0.04, completion: 0.04 },
+    '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,
 );
@@ -176,61 +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-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,
@@ -25,8 +26,14 @@ describe('getValueKey', () => {
     expect(getValueKey('gpt-4-some-other-info')).toBe('8k');
   });
 
-  it('should return undefined for model names that do not match any known patterns', () => {
-    expect(getValueKey('gpt-5-some-other-info')).toBeUndefined();
+  it('should return "gpt-5" for model name containing "gpt-5"', () => {
+    expect(getValueKey('gpt-5-some-other-info')).toBe('gpt-5');
+    expect(getValueKey('gpt-5-2025-01-30')).toBe('gpt-5');
+    expect(getValueKey('gpt-5-2025-01-30-0130')).toBe('gpt-5');
+    expect(getValueKey('openai/gpt-5')).toBe('gpt-5');
+    expect(getValueKey('openai/gpt-5-2025-01-30')).toBe('gpt-5');
+    expect(getValueKey('gpt-5-turbo')).toBe('gpt-5');
+    expect(getValueKey('gpt-5-0130')).toBe('gpt-5');
   });
 
   it('should return "gpt-3.5-turbo-1106" for model name containing "gpt-3.5-turbo-1106"', () => {
@@ -84,6 +91,37 @@ describe('getValueKey', () => {
     expect(getValueKey('gpt-4.1-nano-0125')).toBe('gpt-4.1-nano');
   });
 
+  it('should return "gpt-5" for model type of "gpt-5"', () => {
+    expect(getValueKey('gpt-5-2025-01-30')).toBe('gpt-5');
+    expect(getValueKey('gpt-5-2025-01-30-0130')).toBe('gpt-5');
+    expect(getValueKey('openai/gpt-5')).toBe('gpt-5');
+    expect(getValueKey('openai/gpt-5-2025-01-30')).toBe('gpt-5');
+    expect(getValueKey('gpt-5-turbo')).toBe('gpt-5');
+    expect(getValueKey('gpt-5-0130')).toBe('gpt-5');
+  });
+
+  it('should return "gpt-5-mini" for model type of "gpt-5-mini"', () => {
+    expect(getValueKey('gpt-5-mini-2025-01-30')).toBe('gpt-5-mini');
+    expect(getValueKey('openai/gpt-5-mini')).toBe('gpt-5-mini');
+    expect(getValueKey('gpt-5-mini-0130')).toBe('gpt-5-mini');
+    expect(getValueKey('gpt-5-mini-2025-01-30-0130')).toBe('gpt-5-mini');
+  });
+
+  it('should return "gpt-5-nano" for model type of "gpt-5-nano"', () => {
+    expect(getValueKey('gpt-5-nano-2025-01-30')).toBe('gpt-5-nano');
+    expect(getValueKey('openai/gpt-5-nano')).toBe('gpt-5-nano');
+    expect(getValueKey('gpt-5-nano-0130')).toBe('gpt-5-nano');
+    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');
@@ -155,6 +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', () => {
@@ -207,6 +255,62 @@ describe('getMultiplier', () => {
     );
   });
 
+  it('should return the correct multiplier for gpt-5', () => {
+    const valueKey = getValueKey('gpt-5-2025-01-30');
+    expect(getMultiplier({ valueKey, tokenType: 'prompt' })).toBe(tokenValues['gpt-5'].prompt);
+    expect(getMultiplier({ valueKey, tokenType: 'completion' })).toBe(
+      tokenValues['gpt-5'].completion,
+    );
+    expect(getMultiplier({ model: 'gpt-5-preview', tokenType: 'prompt' })).toBe(
+      tokenValues['gpt-5'].prompt,
+    );
+    expect(getMultiplier({ model: 'openai/gpt-5', tokenType: 'completion' })).toBe(
+      tokenValues['gpt-5'].completion,
+    );
+  });
+
+  it('should return the correct multiplier for gpt-5-mini', () => {
+    const valueKey = getValueKey('gpt-5-mini-2025-01-30');
+    expect(getMultiplier({ valueKey, tokenType: 'prompt' })).toBe(tokenValues['gpt-5-mini'].prompt);
+    expect(getMultiplier({ valueKey, tokenType: 'completion' })).toBe(
+      tokenValues['gpt-5-mini'].completion,
+    );
+    expect(getMultiplier({ model: 'gpt-5-mini-preview', tokenType: 'prompt' })).toBe(
+      tokenValues['gpt-5-mini'].prompt,
+    );
+    expect(getMultiplier({ model: 'openai/gpt-5-mini', tokenType: 'completion' })).toBe(
+      tokenValues['gpt-5-mini'].completion,
+    );
+  });
+
+  it('should return the correct multiplier for gpt-5-nano', () => {
+    const valueKey = getValueKey('gpt-5-nano-2025-01-30');
+    expect(getMultiplier({ valueKey, tokenType: 'prompt' })).toBe(tokenValues['gpt-5-nano'].prompt);
+    expect(getMultiplier({ valueKey, tokenType: 'completion' })).toBe(
+      tokenValues['gpt-5-nano'].completion,
+    );
+    expect(getMultiplier({ model: 'gpt-5-nano-preview', tokenType: 'prompt' })).toBe(
+      tokenValues['gpt-5-nano'].prompt,
+    );
+    expect(getMultiplier({ model: 'openai/gpt-5-nano', tokenType: 'completion' })).toBe(
+      tokenValues['gpt-5-nano'].completion,
+    );
+  });
+
+  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);
@@ -307,10 +411,34 @@ describe('getMultiplier', () => {
   });
 
   it('should return defaultRate if derived valueKey does not match any known patterns', () => {
-    expect(getMultiplier({ tokenType: 'prompt', model: 'gpt-5-some-other-info' })).toBe(
+    expect(getMultiplier({ tokenType: 'prompt', model: 'gpt-10-some-other-info' })).toBe(
       defaultRate,
     );
   });
+
+  it('should return correct multipliers for GPT-OSS models', () => {
+    const models = ['gpt-oss-20b', 'gpt-oss-120b'];
+    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);
+    });
+  });
+
+  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', () => {
@@ -366,6 +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'];
 
@@ -397,6 +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(
@@ -488,6 +1040,9 @@ describe('getCacheMultiplier', () => {
 
 describe('Google Model Tests', () => {
   const googleModels = [
+    'gemini-2.5-pro',
+    'gemini-2.5-flash',
+    'gemini-2.5-flash-lite',
     'gemini-2.5-pro-preview-05-06',
     'gemini-2.5-flash-preview-04-17',
     'gemini-2.5-exp',
@@ -528,6 +1083,9 @@ describe('Google Model Tests', () => {
 
   it('should map to the correct model keys', () => {
     const expected = {
+      'gemini-2.5-pro': 'gemini-2.5-pro',
+      'gemini-2.5-flash': 'gemini-2.5-flash',
+      'gemini-2.5-flash-lite': 'gemini-2.5-flash-lite',
       'gemini-2.5-pro-preview-05-06': 'gemini-2.5-pro',
       'gemini-2.5-flash-preview-04-17': 'gemini-2.5-flash',
       'gemini-2.5-exp': 'gemini-2.5',
@@ -636,6 +1194,15 @@ describe('Grok Model Tests - Pricing', () => {
       );
     });
 
+    test('should return correct prompt and completion rates for Grok 4 model', () => {
+      expect(getMultiplier({ model: 'grok-4-0709', tokenType: 'prompt' })).toBe(
+        tokenValues['grok-4'].prompt,
+      );
+      expect(getMultiplier({ model: 'grok-4-0709', tokenType: 'completion' })).toBe(
+        tokenValues['grok-4'].completion,
+      );
+    });
+
     test('should return correct prompt and completion rates for Grok 3 models with prefixes', () => {
       expect(getMultiplier({ model: 'xai/grok-3', tokenType: 'prompt' })).toBe(
         tokenValues['grok-3'].prompt,
@@ -662,6 +1229,119 @@ describe('Grok Model Tests - Pricing', () => {
         tokenValues['grok-3-mini-fast'].completion,
       );
     });
+
+    test('should return correct prompt and completion rates for Grok 4 model with prefixes', () => {
+      expect(getMultiplier({ model: 'xai/grok-4-0709', tokenType: 'prompt' })).toBe(
+        tokenValues['grok-4'].prompt,
+      );
+      expect(getMultiplier({ model: 'xai/grok-4-0709', tokenType: 'completion' })).toBe(
+        tokenValues['grok-4'].completion,
+      );
+    });
+  });
+});
+
+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,
+    );
   });
 });
 
@@ -681,6 +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',
@@ -758,3 +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/models/userMethods.js

@@ -3,7 +3,7 @@ const bcrypt = require('bcryptjs');
 /**
  * Compares the provided password with the user's password.
  *
- * @param {MongoUser} user - The user to compare the password for.
+ * @param {IUser} user - The user to compare the password for.
  * @param {string} candidatePassword - The password to test against the user's password.
  * @returns {Promise<boolean>} A promise that resolves to a boolean indicating if the password matches.
  */

api/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@librechat/backend",
-  "version": "v0.7.8",
+  "version": "v0.8.1-rc1",
   "description": "",
   "scripts": {
     "start": "echo 'please run this from the root directory'",
@@ -44,19 +44,21 @@
     "@googleapis/youtube": "^20.0.0",
     "@keyv/redis": "^4.3.3",
     "@langchain/community": "^0.3.47",
-    "@langchain/core": "^0.3.60",
+    "@langchain/core": "^0.3.62",
     "@langchain/google-genai": "^0.2.13",
     "@langchain/google-vertexai": "^0.2.13",
     "@langchain/textsplitters": "^0.1.0",
-    "@librechat/agents": "^2.4.46",
+    "@librechat/agents": "^2.4.90",
     "@librechat/api": "*",
     "@librechat/data-schemas": "*",
-    "@node-saml/passport-saml": "^5.0.0",
+    "@microsoft/microsoft-graph-client": "^3.0.7",
+    "@modelcontextprotocol/sdk": "^1.17.1",
+    "@node-saml/passport-saml": "^5.1.0",
     "@waylaidwanderer/fetch-event-source": "^3.0.1",
-    "axios": "^1.8.2",
+    "axios": "^1.12.1",
     "bcryptjs": "^2.4.3",
-    "compression": "^1.7.4",
-    "connect-redis": "^7.1.0",
+    "compression": "^1.8.1",
+    "connect-redis": "^8.1.0",
     "cookie": "^0.7.2",
     "cookie-parser": "^1.4.7",
     "cors": "^2.8.5",
@@ -66,10 +68,11 @@
     "express": "^4.21.2",
     "express-mongo-sanitize": "^2.2.0",
     "express-rate-limit": "^7.4.1",
-    "express-session": "^1.18.1",
+    "express-session": "^1.18.2",
     "express-static-gzip": "^2.2.0",
     "file-type": "^18.7.0",
     "firebase": "^11.0.2",
+    "form-data": "^4.0.4",
     "googleapis": "^126.0.1",
     "handlebars": "^4.7.7",
     "https-proxy-agent": "^7.0.6",
@@ -87,13 +90,12 @@
     "mime": "^3.0.0",
     "module-alias": "^2.2.3",
     "mongoose": "^8.12.1",
-    "multer": "^2.0.1",
+    "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": "^4.96.2",
-    "openai-chat-tokens": "^0.2.8",
+    "openai": "^5.10.1",
     "openid-client": "^6.5.0",
     "passport": "^0.6.0",
     "passport-apple": "^2.0.2",
@@ -117,7 +119,7 @@
   },
   "devDependencies": {
     "jest": "^29.7.0",
-    "mongodb-memory-server": "^10.1.3",
+    "mongodb-memory-server": "^10.1.4",
     "nodemon": "^3.0.3",
     "supertest": "^7.1.0"
   }

api/server/cleanup.js

@@ -1,6 +1,6 @@
-const { logger } = require('~/config');
+const { logger } = require('@librechat/data-schemas');
 
-// WeakMap to hold temporary data associated with requests
+/** WeakMap to hold temporary data associated with requests */
 const requestDataMap = new WeakMap();
 
 const FinalizationRegistry = global.FinalizationRegistry || null;
@@ -23,7 +23,7 @@ const clientRegistry = FinalizationRegistry
         } else {
           logger.debug('[FinalizationRegistry] Cleaning up client');
         }
-      } catch (e) {
+      } catch {
         // Ignore errors
       }
     })
@@ -55,6 +55,9 @@ function disposeClient(client) {
     if (client.responseMessageId) {
       client.responseMessageId = null;
     }
+    if (client.parentMessageId) {
+      client.parentMessageId = null;
+    }
     if (client.message_file_map) {
       client.message_file_map = null;
     }
@@ -334,7 +337,7 @@ function disposeClient(client) {
       }
     }
     client.options = null;
-  } catch (e) {
+  } catch {
     // Ignore errors during disposal
   }
 }

api/server/controllers/AuthController.js

@@ -1,8 +1,8 @@
 const cookies = require('cookie');
 const jwt = require('jsonwebtoken');
 const openIdClient = require('openid-client');
-const { isEnabled } = require('@librechat/api');
 const { logger } = require('@librechat/data-schemas');
+const { isEnabled, findOpenIDUser } = require('@librechat/api');
 const {
   requestPasswordReset,
   setOpenIDAuthTokens,
@@ -11,6 +11,8 @@ const {
   registerUser,
 } = require('~/server/services/AuthService');
 const { findUser, getUserById, deleteAllUserSessions, findSession } = require('~/models');
+const { getGraphApiToken } = require('~/server/services/GraphTokenService');
+const { getOAuthReconnectionManager } = require('~/config');
 const { getOpenIdConfig } = require('~/strategies');
 
 const registrationController = async (req, res) => {
@@ -70,11 +72,17 @@ const refreshController = async (req, res) => {
       const openIdConfig = getOpenIdConfig();
       const tokenset = await openIdClient.refreshTokenGrant(openIdConfig, refreshToken);
       const claims = tokenset.claims();
-      const user = await findUser({ email: claims.email });
-      if (!user) {
+      const { user, error } = await findOpenIDUser({
+        findUser,
+        email: claims.email,
+        openidId: claims.sub,
+        idOnTheSource: claims.oid,
+        strategyName: 'refreshController',
+      });
+      if (error || !user) {
         return res.status(401).redirect('/login');
       }
-      const token = setOpenIDAuthTokens(tokenset, res);
+      const token = setOpenIDAuthTokens(tokenset, res, user._id.toString());
       return res.status(200).send({ token, user });
     } catch (error) {
       logger.error('[refreshController] OpenID token refresh error', error);
@@ -83,7 +91,7 @@ const refreshController = async (req, res) => {
   }
   try {
     const payload = jwt.verify(refreshToken, process.env.JWT_REFRESH_SECRET);
-    const user = await getUserById(payload.id, '-password -__v -totpSecret');
+    const user = await getUserById(payload.id, '-password -__v -totpSecret -backupCodes');
     if (!user) {
       return res.status(401).redirect('/login');
     }
@@ -95,14 +103,29 @@ const refreshController = async (req, res) => {
       return res.status(200).send({ token, user });
     }
 
-    // Find the session with the hashed refresh token
-    const session = await findSession({
-      userId: userId,
-      refreshToken: refreshToken,
-    });
+    /** Session with the hashed refresh token */
+    const session = await findSession(
+      {
+        userId: userId,
+        refreshToken: refreshToken,
+      },
+      { lean: false },
+    );
 
     if (session && session.expiration > new Date()) {
-      const token = await setAuthTokens(userId, res, session._id);
+      const token = await setAuthTokens(userId, res, session);
+
+      // trigger OAuth MCP server reconnection asynchronously (best effort)
+      try {
+        void getOAuthReconnectionManager()
+          .reconnectServers(userId)
+          .catch((err) => {
+            logger.error('[refreshController] Error reconnecting OAuth MCP servers:', err);
+          });
+      } catch (err) {
+        logger.warn(`[refreshController] Cannot attempt OAuth MCP servers reconnection:`, err);
+      }
+
       res.status(200).send({ token, user });
     } else if (req?.query?.retry) {
       // Retrying from a refresh token request that failed (401)
@@ -113,14 +136,59 @@ const refreshController = async (req, res) => {
       res.status(401).send('Refresh token expired or not found for this user');
     }
   } catch (err) {
-    logger.error(`[refreshController] Refresh token: ${refreshToken}`, err);
+    logger.error(`[refreshController] Invalid refresh token:`, err);
     res.status(403).send('Invalid refresh token');
   }
 };
 
+const graphTokenController = async (req, res) => {
+  try {
+    // Validate user is authenticated via Entra ID
+    if (!req.user.openidId || req.user.provider !== 'openid') {
+      return res.status(403).json({
+        message: 'Microsoft Graph access requires Entra ID authentication',
+      });
+    }
+
+    // Check if OpenID token reuse is active (required for on-behalf-of flow)
+    if (!isEnabled(process.env.OPENID_REUSE_TOKENS)) {
+      return res.status(403).json({
+        message: 'SharePoint integration requires OpenID token reuse to be enabled',
+      });
+    }
+
+    // Extract access token from Authorization header
+    const authHeader = req.headers.authorization;
+    if (!authHeader || !authHeader.startsWith('Bearer ')) {
+      return res.status(401).json({
+        message: 'Valid authorization token required',
+      });
+    }
+
+    // Get scopes from query parameters
+    const scopes = req.query.scopes;
+    if (!scopes) {
+      return res.status(400).json({
+        message: 'Graph API scopes are required as query parameter',
+      });
+    }
+
+    const accessToken = authHeader.substring(7); // Remove 'Bearer ' prefix
+    const tokenResponse = await getGraphApiToken(req.user, accessToken, scopes);
+
+    res.json(tokenResponse);
+  } catch (error) {
+    logger.error('[graphTokenController] Failed to obtain Graph API token:', error);
+    res.status(500).json({
+      message: 'Failed to obtain Microsoft Graph token',
+    });
+  }
+};
+
 module.exports = {
   refreshController,
   registrationController,
   resetPasswordController,
   resetPasswordRequestController,
+  graphTokenController,
 };

api/server/controllers/ErrorController.js

@@ -1,40 +0,0 @@
-const { logger } = require('~/config');
-
-//handle duplicates
-const handleDuplicateKeyError = (err, res) => {
-  logger.error('Duplicate key error:', err.keyValue);
-  const field = `${JSON.stringify(Object.keys(err.keyValue))}`;
-  const code = 409;
-  res
-    .status(code)
-    .send({ messages: `An document with that ${field} already exists.`, fields: field });
-};
-
-//handle validation errors
-const handleValidationError = (err, res) => {
-  logger.error('Validation error:', err.errors);
-  let errors = Object.values(err.errors).map((el) => el.message);
-  let fields = `${JSON.stringify(Object.values(err.errors).map((el) => el.path))}`;
-  let code = 400;
-  if (errors.length > 1) {
-    errors = errors.join(' ');
-    res.status(code).send({ messages: `${JSON.stringify(errors)}`, fields: fields });
-  } else {
-    res.status(code).send({ messages: `${JSON.stringify(errors)}`, fields: fields });
-  }
-};
-
-// eslint-disable-next-line no-unused-vars
-module.exports = (err, req, res, next) => {
-  try {
-    if (err.name === 'ValidationError') {
-      return (err = handleValidationError(err, res));
-    }
-    if (err.code && err.code == 11000) {
-      return (err = handleDuplicateKeyError(err, res));
-    }
-  } catch (err) {
-    logger.error('ErrorController => error', err);
-    res.status(500).send('An unknown error occurred.');
-  }
-};

api/server/controllers/ModelController.js

@@ -1,10 +1,11 @@
+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
+ * @returns {Promise<TModelsConfig>} The models config.
  */
 const getModelsConfig = async (req) => {
   const cache = getLogStores(CacheKeys.CONFIG_STORE);