librechat.example.yaml

# For more information, see the Configuration Guide:
# https://www.librechat.ai/docs/configuration/librechat_yaml

# Configuration version (required)
version: 1.3.18

# Cache settings: Set to true to enable caching
cache: true

# Browser telemetry and session recording are independent opt-ins. Collector URL,
# authentication and service settings remain in .env. YAML flags override .env;
# omitting them preserves the corresponding environment settings.
# stackTraceLimit (1 to 1000) sets how many frames each error stack records; unset keeps
# Node's default of 10, or --stack-trace-limit from NODE_OPTIONS.
# telemetry:
#   stackTraceLimit: 50
#   rum:
#     enabled: true
#     sessionReplay:
#       enabled: false # Explicitly opt in to masked DOM/input recordings.

# Client limits: request deadlines in milliseconds (1 to 3600000) and upload concurrency. Every field is optional and defaults
# to the value shown, which is the behavior when the block is absent. Raise a deadline when your
# infrastructure legitimately needs longer.
# clientLimits:
#   refreshMs: 30000     # token refresh; on expiry the user is sent to login
#   ttsMs: 60000         # time for the text-to-speech endpoint to start responding
#   sharepointMs: 300000 # download of one SharePoint file
#   cloudfrontMs: 15000  # CloudFront signed-cookie refresh
#   uploadConcurrency: 3 # project files uploaded at once (1 to 10)

# Chat Projects: the ceilings a single project may reach. Every field is optional and
# defaults to the value shown, which is the behavior when the block is absent.
projects:
  # Reference files that may be attached to one project (maximum 500).
  maxFiles: 50
  # Characters of project instructions stored and sent as guidance (maximum 200000).
  maxInstructionsLength: 16000
  # Characters of the project description shown in the workspace and sidebar (maximum 10000).
  maxDescriptionLength: 1000

# Tool-call previews: a long conversation's tool outputs, arguments and subagent transcripts
# can run to megabytes, though their cards render collapsed. The web client asks for bounded
# previews when it loads a conversation (the start and end of each long output, arguments
# with their long strings shortened, no subagent transcripts) and loads a call in full when
# the reader opens it. Clients that do not ask, exports and share links get full content.
# Every field is optional and defaults to the value shown; enabled: false always sends the
# full payload.
# toolCallPreviews:
#   enabled: true
#   outputChars: 512   # characters of each output kept, half from the start and half from the end
#   argsChars: 512     # characters of serialized arguments kept; JSON stays valid JSON

# Stored user credentials (tool and web search keys, MCP custom user variables) are
# written with a random IV per value ("v3", the default). Both formats are always read.
# During a rolling upgrade of a multi-replica deployment, set "legacy" until every
# replica runs a release that reads v3, then remove it. A rollback to a release that
# predates v3 cannot read credentials saved in the v3 format.
# credentials:
#   writeFormat: v3

# Langfuse connections are managed through Settings > Langfuse when available.
# That flow verifies the credentials and stores the secret key encrypted; do not
# place a plaintext langfuse.secretKey in this file. Environment-managed central
# credentials and optional fanout routing are documented in .env.example.
#
# Self-hosted Langfuse behind an authenticating proxy or gateway can be given
# custom request headers. They are sent on every outbound Langfuse request —
# trace and media export, feedback scores, and credential verification.
# Values support ${ENV_VAR} interpolation; a header whose variable is unset is
# dropped with a warning rather than sent as a literal placeholder.
#
# These are deployment-level: trace export batches spans from every user through
# a single exporter, so unlike endpoints.custom headers they cannot carry
# per-user placeholders such as {{LIBRECHAT_USER_ID}}.
#
# Values are masked in admin config reads and in the startup config log, but
# prefer ${ENV_VAR} references over literal credentials here regardless.
#
# Scope: these are sent only when the deployment configures exactly ONE Langfuse
# origin (a self-hosted base URL, or a single tenant destination URL), and only
# to that origin. The map has no way to say which endpoint it authenticates to,
# so a deployment configuring several origins — e.g. a fanout collector plus a
# separate central host — gets a warning and no headers, rather than having a
# gateway credential sent somewhere it was not meant for.
#
# Fanout deployments additionally need collector support: the gateway forwards
# only Authorization upstream, so a tenant Langfuse behind its own proxy is not
# covered even when the collector receives these.
#
# Traces carry the internal user id as the Langfuse userId and no user or
# request metadata unless langfuse.trace opts in. userIdField picks the user
# field that becomes the trace userId (id, email, username, name, openidId,
# samlId, ldapId, googleId, githubId, discordId, appleId, facebookId); a user
# without a value for that field keeps the internal id. The two allowlists copy
# fields into trace metadata as librechat.user.<field> (the userId fields plus
# role and provider) and librechat.conversation.id, librechat.endpoint,
# librechat.endpoint.type, librechat.provider, librechat.model,
# librechat.model.label, librechat.spec.
#
# Temporary chats, including every chat when interface.retentionMode is
# "ephemeral", are not traced and their feedback is not scored unless
# langfuse.trace.temporaryChats is true.
#
# langfuse:
#   headers:
#     CF-Access-Client-Id: "${CF_ACCESS_CLIENT_ID}"
#     CF-Access-Client-Secret: "${CF_ACCESS_CLIENT_SECRET}"
#   trace:
#     userIdField: email
#     userMetadataFields: [email, username, role, provider]
#     conversationMetadataFields: [conversationId, endpoint, model, modelLabel, spec]
#     temporaryChats: false

# File storage configuration
# Single strategy for all file types (legacy format, still supported)
# fileStrategy: "s3"
# Maximum rows returned when GET /files receives an explicit `limit` query parameter.
# fileListLimit: 100

# Granular file storage strategies (new format - recommended)
# Allows different storage strategies for different file types
# fileStrategy:
#   avatar: "s3"        # Storage for user/agent avatar images
#   image: "firebase"   # Storage for uploaded images in chats
#   document: "local"   # Storage for document uploads (PDFs, text files, etc.)

# Available strategies: "local", "s3", "firebase", "azure_blob", "cloudfront"
# If not specified, defaults to "local" for all file types
# You can mix and match strategies based on your needs:
# - Use S3 for avatars for fast global access
# - Use Firebase for images with automatic optimization
# - Use local storage for documents for privacy/compliance
# - Use CloudFront for CDN-accelerated delivery (requires S3 + cloudfront config below)

# CloudFront CDN Configuration (optional)
# Use when fileStrategy: "cloudfront" or fileStrategies includes cloudfront
# Requires: AWS_REGION, AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_BUCKET_NAME
# For signed cookies and direct download URLs: CLOUDFRONT_KEY_PAIR_ID, CLOUDFRONT_PRIVATE_KEY
# cloudfront:
#   domain: "https://cdn.example.com"       # CloudFront domain (CNAME recommended for cookies)
#   distributionId: "E1234ABCD"             # Required if invalidateOnDelete is true
#   invalidateOnDelete: false               # Create cache invalidation on file delete
#   imageSigning: "none"                    # "none" (public) | "cookies" (signed cookies)
#   # When imageSigning: "cookies", API + CloudFront must share a parent domain.
#   # Cookies are path-scoped to inline assets only:
#   #   /i/... private uploaded/generated images, user-scoped
#   #   /a/... tenant-visible avatars, tenant-scoped when tenantId is present
#   # Downloads, documents, uploads, and code outputs stay outside /i and /a and
#   # use backend-authorized signed URLs instead of signed cookies.
#   #   API: api.example.com, CloudFront CNAME: cdn.example.com, cookieDomain: ".example.com"
#   cookieDomain: ".example.com"            # Required for "cookies" - shared parent domain
#   cookieExpiry: 1800                      # Cookie lifetime in seconds (max: 604800 / 7 days, default: 1800 / 30 min)
#   urlExpiry: 3600                         # Signed CloudFront download URL lifetime in seconds
#   # Optional multi-region S3/CloudFront layout. Default: false.
#   # When enabled, new object keys include:
#   #   /i/r/{storageRegion}/t/{tenantId}/images/{userId}/{file}   (private inline images)
#   #   /a/r/{storageRegion}/t/{tenantId}/avatars/{userId}/{file}  (tenant-visible avatars)
#   #   /r/{storageRegion}/t/{tenantId}/{basePath}/{userId}/{file} (non-inline files)
#   # storageRegion defaults to AWS_REGION when omitted, but only affects new keys
#   # when includeRegionInPath is true. Existing files are not moved automatically.
#   # LibreChat does not configure CloudFront origins, Route53, or regional routing.
#   storageRegion: "us-east-2"
#   includeRegionInPath: false
#   # Direct-download filename/content-type overrides require the CloudFront cache/origin
#   # request policy to forward and cache on response-content-disposition and
#   # response-content-type query strings to S3.
#   # Recommended for download paths: attach a CloudFront response headers policy
#   # with X-Content-Type-Options: nosniff and CSP default-src 'none'.

# Skill sync configuration (optional)
# GitHub tokens are referenced from environment variables. Put the token in
# `.env`, then reference it here with `token: '${GITHUB_SKILLS_TOKEN}'`. Use a
# GitHub fine-grained personal access token scoped to the selected repository
# with read-only Contents and Metadata permissions.
# skillSync:
#   github:
#     enabled: false
#     intervalMinutes: 60
#     runOnStartup: true
#     sources:
#       - id: librechat-skills
#         owner: your-org
#         repo: your-skills-repo
#         ref: main
#         paths:
#           - skills
#         # Number of directory levels below each configured path to scan for
#         # `SKILL.md`. Use 2 for repos shaped like `skills/<category>/<skill>`.
#         skillDiscoveryDepth: 2
#         token: '${GITHUB_SKILLS_TOKEN}'
#         # Optional. Owns the mirrored skills under the given tenant so they are
#         # created and shared within that tenant. Required for visibility when
#         # tenant isolation is enabled. Omit for single-tenant deployments.
#         # Treat as immutable per source id: changing (or adding/removing) the
#         # tenantId later leaves previously mirrored skills in the old tenant,
#         # where this source's sync can no longer see or clean them up. To move a
#         # source between tenants, delete its mirrored skills in the old tenant
#         # first, or use a new source id for the new tenant.
#         # tenantId: your-tenant-id

# Custom interface configuration
interface:
  customWelcome: 'Welcome to LibreChat! Enjoy your experience.'
  # What heads the welcome screen when an agent, assistant or model spec is selected (default: entity).
  # 'entity' shows its name; 'greeting' shows the time-of-day greeting (or customWelcome) with the
  # user's name, for deployments where the header selector already names the agent.
  # landingHeading: entity
  # Show the generic disclaimer and policy links on the welcome screen (default: true).
  # true places them at the bottom of the page, 'composer' directly under the composer, and false
  # hides them. When false, a CUSTOM_FOOTER still renders there, as it does in conversations.
  # landingFooter: true
  # Which responses show the author's avatar and name above their content (default: always).
  # 'whenDifferent' drops them when the header's model selector already shows that agent; a
  # response from another agent keeps them. The name stays available to screen readers.
  # messageAuthor: always
  # Allow renaming a running chat or one with a placeholder title (default: true).
  # Set to false during a rolling upgrade, until ALL API replicas are upgraded and old
  # title-generation jobs have drained. While false, rename is disabled for running chats
  # and unowned placeholder titles; other actions stay available.
  # runningChatRename: true
  # Minimum interval between syntax-highlighting passes while streamed code changes (default: 300 ms)
  # codeHighlightThrottleMs: 300
  # How long a conversation's message history stays cached in the browser after leaving it (default: 60000 ms),
  # and how many of the most recently left conversations keep that grace (default: 1). Older ones are refetched.
  # historyCacheTtlMs: 60000
  # historyCacheRecent: 1
  # Deployment theme applied to every user, in both light and dark mode (default: unset).
  # It is not saved to the browser, outranks REACT_APP_THEME_* colors and stored themes,
  # and yields to the high-contrast modes. Either a bundled theme name (librechat, clickhouse):
  # theme: clickhouse
  # or an inline definition. Colors are space-separated RGB triplets keyed by rgb-* token:
  # theme:
  #   version: 1
  #   name: acme
  #   modes:
  #     light:
  #       colors:
  #         rgb-surface-primary: '255 255 255'
  #         rgb-surface-submit: '21 21 21'
  #       appearance:
  #         controlRadius: '0.25rem'
  #     dark:
  #       colors:
  #         rgb-surface-primary: '31 31 28'
  #         rgb-surface-submit: '250 255 105'
  # Enable/disable file search as a chatarea selection (default: true)
  # Note: This setting does not disable the Agents File Search Capability.
  # To disable the Agents Capability, see the Agents Endpoint configuration instead.
  fileSearch: true
  # Privacy policy settings
  privacyPolicy:
    externalUrl: 'https://librechat.ai/privacy-policy'
    openNewTab: true

  # Terms of service
  termsOfService:
    externalUrl: 'https://librechat.ai/tos'
    openNewTab: true
    modalAcceptance: true
    modalTitle: 'Terms of Service for LibreChat'
    modalContent: |
      # Terms and Conditions for LibreChat

      *Effective Date: February 18, 2024*

      Welcome to LibreChat, the informational website for the open-source AI chat platform, available at https://librechat.ai. These Terms of Service ("Terms") govern your use of our website and the services we offer. By accessing or using the Website, you agree to be bound by these Terms and our Privacy Policy, accessible at https://librechat.ai//privacy.

      ## 1. Ownership

      Upon purchasing a package from LibreChat, you are granted the right to download and use the code for accessing an admin panel for LibreChat. While you own the downloaded code, you are expressly prohibited from reselling, redistributing, or otherwise transferring the code to third parties without explicit permission from LibreChat.

      ## 2. User Data

      We collect personal data, such as your name, email address, and payment information, as described in our Privacy Policy. This information is collected to provide and improve our services, process transactions, and communicate with you.

      ## 3. Non-Personal Data Collection

      The Website uses cookies to enhance user experience, analyze site usage, and facilitate certain functionalities. By using the Website, you consent to the use of cookies in accordance with our Privacy Policy.

      ## 4. Use of the Website

      You agree to use the Website only for lawful purposes and in a manner that does not infringe the rights of, restrict, or inhibit anyone else's use and enjoyment of the Website. Prohibited behavior includes harassing or causing distress or inconvenience to any person, transmitting obscene or offensive content, or disrupting the normal flow of dialogue within the Website.

      ## 5. Governing Law

      These Terms shall be governed by and construed in accordance with the laws of the United States, without giving effect to any principles of conflicts of law.

      ## 6. Changes to the Terms

      We reserve the right to modify these Terms at any time. We will notify users of any changes by email. Your continued use of the Website after such changes have been notified will constitute your consent to such changes.

      ## 7. Contact Information

      If you have any questions about these Terms, please contact us at contact@librechat.ai.

      By using the Website, you acknowledge that you have read these Terms of Service and agree to be bound by them.

  modelSelect: true
  parameters: true
  presets: true
  prompts:
    use: true
    create: true
    share: false
    public: false
  bookmarks: true
  multiConvo: true
  # Allow the artifacts pane to be moved into its own browser window
  # (desktop only; the mobile sheet is unaffected). Default: true.
  artifactUndocking: true
  # Ask each viewer before loading Google Tag Manager (ANALYTICS_GTM_ID).
  # Set false when the deployment settles consent itself, e.g. internal use. Default: true.
  # analyticsConsent: true
  agents:
    use: true
    create: true
    share: false
    public: false
  # Allow Lia, the welcome screen mascot. Users still opt in from Settings (default: true).
  mascot: true
  # Scheduled chats are experimental and disabled unless explicitly enabled.
  # A deployment with Redis-backed resumable streams can run this on every replica.
  # A single-process deployment without Redis must also set
  # `SCHEDULES_SINGLE_PROCESS=true`; unsafe multi-replica writes fail closed.
  # Scheduled agents that can pause require both `USE_REDIS_STREAMS=true` for
  # shared action state and a durable shared checkpointer for graph continuation.
  # MongoDB is currently the built-in durable checkpointer (and the default).
  # schedules:
  #   use: true
  #   create: true
  #   maxPerUser: 10
  #   minIntervalMinutes: 60
  #   autoDisableAfterFailures: 5
  #   # Maximum occurrences concurrently passing readiness admission per replica (1-100).
  #   admissionConcurrency: 20
  #   fireConcurrency: 5
  #   # Maximum MCP readiness connections opened at once by one schedule admission (1-10).
  #   mcpPreflightConcurrency: 3
  #   # Maximum wall-clock time for one MCP readiness admission (1000-600000 ms).
  #   mcpPreflightTimeoutMs: 300000
  #   # Require every schedule to be filed under a chat project. Enforced on
  #   # create/update AND at each fire, so turning it on stops (auto-disables)
  #   # schedules that predate it rather than letting their runs land loose.
  #   requireProject: false
  #   # Pin every scheduled run to ONE chat project, ignoring the user's choice.
  #   # Implies `requireProject`. Chat projects are user-owned, so a value set here
  #   # only makes sense as a per-user or per-role config override.
  #   # projectId: '000000000000000000000000'
  peoplePicker:
    users: true
    groups: true
    roles: true
  marketplace:
    use: false
  fileCitations: true
  # Show the thumbs up/thumbs down feedback buttons on responses (default: true)
  feedback: true
  # Unseen-reply alerts: what this deployment lets a reader turn on. Each field gates a
  # capability; the preference itself stays per device, because notification permission and
  # audio output belong to the machine the reader is sitting at. Sidebar unread dots and
  # Mark as unread are not gated here, they are part of the conversation list.
  # replyNotifications:
  #   tabBadge: true # Allow the unseen count in the tab title and favicon (default: true)
  #   desktop: true # Allow readers to turn on desktop notifications for replies (default: true)
  #   sound: true # Allow readers to turn on the reply chime (default: true)
  #   # How many conversations one background poll looks at (1-100, default: 100). The list's
  #   # own maximum page is the ceiling, so covering a deployment whose replies outpace one
  #   # page is not a matter of raising this.
  #   pollLimit: 100
  #   # Milliseconds between list checks while a tab is away (10000-600000, default: 30000).
  #   pollIntervalMs: 30000
  #   # Milliseconds between list refreshes while a tab is focused (60000-300000, default: 300000).
  #   # It renews the snapshot the unread count reads, so it cannot be slower than five minutes.
  #   focusedRefreshMs: 300000
  # Conversation trace viewer: a waterfall of the model calls and tool spans behind
  # each response, read from the deployment's Langfuse project. The control only
  # appears on the requesting user's own conversations with a sampled trace, and
  # needs a Langfuse release that serves the v2 Observations API.
  # traceViewer:
  #   enabled: false
  #   # Traces are matched to users by the internal user id, so no trace is shown while
  #   # langfuse.trace.userIdField exports another user field.
  #   # Return observation input, output and metadata in the record inspector. Input
  #   # carries system prompts, agent instructions and tool definitions, which a
  #   # user chatting with a shared agent cannot otherwise see.
  #   showInputOutput: false
  #   # Name the tools of each tool round from the round's own record. This adds
  #   # requests to Langfuse per listed page, and Langfuse returns each round's full
  #   # input and output to serve them, though only the tool names are kept and sent
  #   # on; arguments and results stay behind showInputOutput. When off, a round is
  #   # named only where the conversation's messages can be matched to the trace.
  #   showToolNames: false
  #   # Observations read per request (1-10000); older records load on demand.
  #   maxRecords: 1000
  #   # Characters kept from each input, output and metadata value (1-1000000).
  #   maxContentLength: 50000
  #   # Trace reads one user may start per minute (1-1000).
  #   requestsPerMinute: 30
  #   # Budget for each request to Langfuse, in milliseconds (1000-300000).
  #   requestTimeoutMs: 10000
  # Tools pinned to the prompt bar by default for all users.
  # Only seeds the initial state — once a user pins/unpins a tool, their choice is kept.
  # Valid tool keys: artifacts, execute_code, web_search, file_search, skills.
  # Use 'mcp' (or a specific MCP server name) to pin the MCP servers dropdown.
  # When omitted, tools start unpinned and the MCP dropdown keeps its default (pinned).
  # defaultPinnedTools:
  #   - 'artifacts'
  #   - 'execute_code'
  #   - 'mcp'
  # Remote Agents configuration
  # Controls user permissions for remote agents with external API support
  # remoteAgents:
  #   use: false
  #   create: false
  #   share: false
  #   public: false
  # MCP Servers configuration example
  # Shared Links configuration
  # Controls user permissions for shared links (e.g. sharing conversations via link)
  # sharedLinks:
  #   create: false
  #   share: true
  #   public: true # Allows users to toggle "share with everyone" for their links. Whether anonymous access is permitted is controlled by ALLOW_SHARED_LINKS_PUBLIC.
  #   snapshotFiles: true # Snapshot files referenced by a shared chat so viewers can preview/download them via the link. Enabled by default; the SHARED_LINKS_SNAPSHOT_FILES env var overrides this.
  # mcpServers:
  #   # Poll only while MCP controls are visible, in milliseconds (0 disables polling).
  #   toolsRefreshInterval: 300000
  #   statusRefreshInterval: 30000
  # Controls user permissions for MCP (Model Context Protocol) server management
  # - use: Allow users to use configured MCP servers
  # - create: Allow users to create and manage new MCP servers
  # - share: Allow users to share MCP servers with other users
  # - public: Allow users to share MCP servers publicly (with everyone)

  # Creation / edit MCP server config Dialog config example
  # trustCheckbox:
  #   label:
  #     en: 'I understand and I want to continue'
  #     de: 'Ich verstehe und möchte fortfahren'
  #     de-DE: 'Ich verstehe und möchte fortfahren' # You can narrow translation to regions like (de-DE or de-CH)
  #   subLabel:
  #     en: |
  #       Librechat hasn't reviewed this MCP server. Attackers may attempt to steal your data or trick the model into taking unintended actions, including destroying data. <a href="https://google.de" target="_blank"><strong>Learn more.</strong></a>
  #     de: |
  #       LibreChat hat diesen MCP-Server nicht überprüft. Angreifer könnten versuchen, Ihre Daten zu stehlen oder das Modell zu unbeabsichtigten Aktionen zu verleiten, einschließlich der Zerstörung von Daten. <a href="https://google.de" target="_blank"><strong>Mehr erfahren.</strong></a>

  # Temporary chat retention period in hours (default: 720, min: 1, max: 8760)
  # temporaryChatRetention: 1
  # Regular chat retention in hours under retentionMode: "all" (min: 1, max: 8760).
  # Defaults to the temporary chat retention policy when omitted.
  # generalChatRetention: 2160 # 90 days, independently of temporary chats
  # Existing stored deadlines are not migrated when these settings change.
  # Retention mode: "temporary" (default) applies expiry only to chats users mark temporary;
  # "all" applies expiry to all data types while keeping chats visible in history;
  # "ephemeral" forces every chat to be temporary (always on, not user-toggleable) and applies expiry to all data.
  # Before switching from "all"/"ephemeral" back to "temporary", remove retention deadlines from non-temporary data
  # that should stop expiring:
  # db.conversations.updateMany({ isTemporary: false, expiredAt: { $ne: null } }, { $unset: { expiredAt: 1 } })
  # db.messages.updateMany({ isTemporary: false, expiredAt: { $ne: null } }, { $unset: { expiredAt: 1 } })
  # MongoDB does not drop superseded indexes automatically. After upgrading, old Meili indexes
  # such as "_meiliIndex_1_expiredAt_1" can be dropped from conversations/messages once the new
  # "_meiliIndex_1_isTemporary_1_expiredAt_1" indexes exist.
  # retentionMode: "temporary"
  # Set retainAgentFiles to true to keep persistent agent resource files from expiring under
  # retentionMode: "all"; non-agent files still expire.
  # retainAgentFiles: false

# Example Cloudflare turnstile (optional)
#turnstile:
#  siteKey: "your-site-key-here"
#  options:
#    language: "auto"    # "auto" or an ISO 639-1 language code (e.g. en)
#    size: "normal"      # Options: "normal", "compact", "flexible", or "invisible"

# Example Registration Object Structure (optional)
# Changing the registered email address from Settings > Account.
# Omitted, these fall back to ALLOW_EMAIL_CHANGE and a 15-minute link.
# emailChange:
#   enabled: true
#   tokenTTLSeconds: 900

# Passkey (WebAuthn) enrollment limits.
# Omitted, perUserMax falls back to MAX_PASSKEYS_PER_USER, then 20.
# passkeys:
#   perUserMax: 20

registration:
  socialLogins: ['github', 'google', 'discord', 'openid', 'facebook', 'apple', 'saml']
  # allowedDomains:
  # - "gmail.com"
  # How long a started social login may take to return from the provider (ms, default 600000)
  # oauthStateTtlMs: 600000
  # OpenID discovery retries when the provider is unreachable (overrides OPENID_DISCOVERY_RETRY_* env vars)
  # openidDiscovery:
  #   startupAttempts: 1   # attempts before startup continues; 0 = background retries only
  #   retryDelayMs: 5000   # delay between startup and background attempts

# Example Balance settings
# balance:
#   enabled: false
#   startBalance: 20000
#   autoRefillEnabled: false
#   refillIntervalValue: 30 # Reset mode requires a positive integer
#   refillIntervalUnit: 'days'
#   refillAmount: 10000
#   # Deploy reset-capable servers to every replica before selecting 'reset'.
#   refillMode: 'add' # 'reset' replaces the allowance each period without rollover
#   reservationTtlMs: 1800000  # How long an in-flight request's reserved credits count if never released
#   display: 'credits'  # credits | currency (uses interface.currency) | percent (share of the allotment used)

# Example Transactions settings
# Controls whether to save transaction records to the database
# Default is true (enabled)
#transactions:
#  enabled: false
# Note: If balance.enabled is true, transactions will always be enabled
# regardless of this setting to ensure balance tracking works correctly

# Speech (STT/TTS) outbound requests to operator-provided target URLs are SSRF-guarded
# at connect time: private, loopback, link-local, and cloud-metadata targets are blocked
# by default. To point STT/TTS at a private or self-hosted service (LocalAI, a self-hosted
# Whisper server), add its host:port to `allowedAddresses` on the `stt` / `tts` section.
# SECURITY: `allowedAddresses` entries are trusted before the private-IP check. A listed
# host:port is permitted even when it resolves to a private IP, so list only hosts you fully
# control and that cannot be repointed by an attacker. Do not list attacker-controllable or
# DNS-rebindable hostnames, because doing so re-opens the private-address path this guard
# closes. Prefer a private IP literal over a hostname when exempting a private target. Entries
# must include a port (`host:port`, `private.ip:port`, or `[ipv6]:port`); do not use URLs, paths,
# CIDR ranges, bare hosts/IPs, or public IP literals.
# When a forward proxy is configured (PROXY / HTTP(S)_PROXY), it performs DNS and egress in its
# own network context, so these requests are delegated to it and it must be SSRF-enforcing; the
# connect-time guard only covers direct, non-proxied connections.
# speech:
#   tts:
#     maxInputChars: 20000 # longest text one request may synthesize (each 1,000 chars is a provider call)
#     openai:
#       url: ''
#       apiKey: '${TTS_API_KEY}'
#       model: ''
#       voices: ['']
#     allowedAddresses:
#       - 'localhost:8020'
#       - '127.0.0.1:8020'
#
#   stt:
#     openai:
#       url: ''
#       apiKey: '${STT_API_KEY}'
#       model: ''
#     allowedAddresses:
#       - 'localhost:8000'
#       - '127.0.0.1:8000'

# OCR (Mistral / Mistral-compatible) outbound requests to `ocr.baseURL` are SSRF-guarded at
# connect time with the same default-deny for private targets. To point OCR at a private or
# self-hosted Mistral-compatible service, add its host:port to `allowedAddresses`. The same
# trust caveat as speech applies: a listed host:port is trusted before the private-IP check,
# so list only hosts you fully control and that cannot be repointed by an attacker. Entries
# must include a port and must not be URLs, paths, CIDR ranges, bare hosts/IPs, or public IP
# literals.
# ocr:
#   baseURL: '${OCR_BASEURL}'
#   apiKey: '${OCR_API_KEY}'
#   allowedAddresses:
#     - 'localhost:8080'
#     - '127.0.0.1:8080'

# Worker threads that hash passwords and auth tokens off the event loop.
# passwordHashing:
#   maxWorkers: 2 # default: one less than the CPU count, at most 4

# Outbound call budgets, in milliseconds. Each omitted key keeps the default shown.
# timeouts:
#   ragMs: 30000 # RAG API queries for file search and message context
#   ocrMs: 300000 # each OCR provider call
#   actionsMs: 300000 # each action (OpenAPI tool) HTTP call
#   moderationMs: 10000 # the OpenAI moderation check before a chat turn
#   imageFetchMs: 30000 # reading a stored image, by URL or from blob storage, to encode it for a provider
#   toolsMs: 60000 # each call a built-in tool makes to its API (weather, Wolfram, web search)
#   speechMs: 300000 # each text-to-speech or speech-to-text provider request
#   imageGenerationMs: 300000 # each Stable Diffusion image generation request

# Newest violations kept per user in the general violation log.
# violationLog:
#   maxEntries: 100

# Largest pageSize accepted when reading a conversation's messages.
# messages:
#   maxPageSize: 1000 # default: 1000

# Upper bounds on independent lookups a request runs at once (1 to 32). Each omitted key keeps the default shown.
# concurrency:
#   connectedAgentLoads: 4 # connected agents initialized together per level of a handoff graph
#   mcpCatalogLookups: 4 # MCP tool catalog reads when assembling an ephemeral or added agent
#   skillNameLookups: 8 # model spec skill name resolutions
#   skillFileInspections: 4 # bundled skill file inspections before a skill is primed
#   resumeAgentLoads: 4 # agent reads while building the resume snapshot of a paused run

# rateLimits:
#   # Per-user MCP App browser-route limits. Each limit uses a fixed one-minute window.
#   mcpApps:
#     resourcesPerMinute: 120
#     toolCallsPerMinute: 60
#   # Shared account budget for all authenticated 2FA management operations.
#   # Always active; successful and failed requests count. Uses Redis when enabled.
#   # Minimum 3, so enable -> verify -> confirm can complete within one window.
#   twoFactorManagement:
#     requestsPerFiveMinutes: 7
#   # Authenticated agent-event admission has its own API-key-principal bucket.
#   agentEvents:
#     userMax: 40
#     userWindowInMinutes: 1
#   fileUploads:
#     ipMax: 100
#     ipWindowInMinutes: 60  # Rate limit window for file uploads per IP
#     userMax: 50
#     userWindowInMinutes: 60  # Rate limit window for file uploads per user
#   conversationsImport:
#     ipMax: 100
#     ipWindowInMinutes: 60  # Rate limit window for conversation imports per IP
#     userMax: 50
#     userWindowInMinutes: 60  # Rate limit window for conversation imports per user
#   # Asking for a change of the registered email, per authenticated user.
#   emailChange:
#     userMax: 3
#     userWindowInMinutes: 2
#   # Opening a verification link. The endpoint is unauthenticated, so the source
#   # address is bounded as well as the account the link names.
#   emailChangeConfirm:
#     ipMax: 20
#     ipWindowInMinutes: 2
#     userMax: 2
#     userWindowInMinutes: 2

# Agent Actions domain restrictions (OpenAPI spec validation)
# SECURITY: If not configured, SSRF targets are blocked (localhost, private IPs, .internal/.local TLDs).
# Prefer `allowedAddresses` for permitting internal targets — adding a private IP to
# `allowedDomains` switches the field into strict-whitelist mode and blocks every
# public destination not also listed.
# Supports wildcards: '*.example.com' and protocol/port restrictions: 'https://api.example.com:8443'
actions:
  allowedDomains:
    - 'swapi.dev'
    - 'librechat.ai'
    - 'google.com'
    # - 'http://10.225.26.25:7894'  # Internal IP with protocol/port (uncomment if needed)
  # `allowedAddresses` is an SSRF exemption list, NOT a strict whitelist.
  # Hostname/IP + port pairs listed here bypass the default-deny block for that
  # one private/loopback/link-local service. Public domains continue to work
  # normally — listing private targets here does not restrict access to anything else.
  #
  # Entries must include a port: `host:port`, `private.ip:port`, or `[ipv6]:port`.
  # Do not use URLs, paths, CIDR ranges, bare hosts/IPs, or public IP literals.
  # Public IP literals are rejected at config load (the field is scoped to
  # private IP space; public IPs aren't SSRF targets).
  #
  # NOTE on hostnames: a hostname entry trusts whatever IP that name resolves to
  # on the listed port. If DNS for that name is hijacked or rotated to a different
  # private IP, the exemption follows. Only list hostnames whose DNS you control.
  # Prefer literal IPs when you can.
  # allowedAddresses:
  #   - 'host.docker.internal:11434'
  #   - '127.0.0.1:11434'
  #   - '10.0.0.5:8080'

# Custom endpoint baseURL exemption list
# SECURITY: User-provided baseURLs (`baseURL: 'user_provided'`) are validated against
# the same SSRF block as Actions and MCP. If your users legitimately point at private
# services (self-hosted Ollama, internal LLM gateway, etc.), list those hostname/IP
# + port pairs here so the validator allows them through. Public destinations are
# unaffected.
#
# Entries must include a port: `host:port`, `private.ip:port`, or `[ipv6]:port`.
# Do not use URLs, paths, CIDR ranges, bare hosts/IPs, or public IP literals.
# Hostname entries trust whatever IP they resolve to on the listed port — only
# list names whose DNS you control.
# endpoints:
#   allowedAddresses:
#     - 'localhost:11434'
#     - '127.0.0.1:11434'
#     - 'ollama:11434'
#     - '10.0.0.5:8080'

# MCP Server domain restrictions for remote transports (SSE, WebSocket, HTTP)
# SECURITY: If not configured, SSRF targets are blocked (localhost, private IPs, .internal/.local TLDs).
# Prefer `allowedAddresses` for permitting internal targets — adding a private host to
# `allowedDomains` switches the field into strict-whitelist mode and blocks every
# public destination not also listed.
# Supports wildcards: '*.example.com' matches 'api.example.com', 'staging.example.com', etc.
# Supports protocol/port restrictions: 'https://api.example.com:8443' restricts to specific protocol/port.
# mcpSettings:
#   # New MCP Apps require explicit opt-in. If omitted, legacy inline HTML remains enabled;
#   # false disables both MCP Apps and legacy inline HTML.
#   apps: true
#   oauthFailureRetentionMs: 86400000 # how long a failed OAuth reconnection is remembered
#   allowedDomains:
#     - 'host.docker.internal'    # Docker host access (required for Docker setups)
#     - 'localhost'               # Local development
#     - '*.example.com'           # Wildcard subdomain
#     - 'https://secure.api.com'  # Protocol-restricted
#     - 'http://internal:8080'    # Protocol and port restricted
#   # allowedAddresses is an SSRF exemption list (private-IP-space only).
#   # Hostname/IP + port pairs listed here bypass the default-deny block for that
#   # one private service; public destinations remain reachable. Useful when you
#   # want default SSRF protection AND specific internal MCP servers. Entries must
#   # include a port (`host:port`, `private.ip:port`, or `[ipv6]:port`) and must
#   # not be URLs, paths, CIDR ranges, bare hosts/IPs, or public IP literals.
#   # Hostname entries trust whatever IP they resolve to on the listed port.
#   allowedAddresses:
#     - 'host.docker.internal:8080'
#     - '127.0.0.1:8080'

# Deployment-owned MCP App sandbox settings. These cannot be overridden by role, group, or user
# configuration. Set url to a dedicated origin routed to /api/mcp/sandbox. Defaults are shown.
# mcpAppSandbox:
#   url: https://mcp-sandbox.example.com/api/mcp/sandbox
#   maxSourcesPerDirective: 32
#   maxSerializedLength: 4096
#   maxPersistedAppBytes: 1048576
#   maxAdmissionRequestsPerMinute: 240
#   maxActiveViews: 3  # simultaneous interactive App views per browser
#   maxActionPreviewChars: 16384  # App tool arguments and chat message preview

# Example MCP Servers Object Structure
# mcpServers:
#   everything:
#     # type: sse # type can optionally be omitted
#     url: http://localhost:3001/sse
#     # proxy: "${MCP_PROXY_URL}"  # optional outbound proxy (http/https/socks/socks5)
#     timeout: 60000  # 1 minute timeout for this server, this is the default timeout for MCP servers.
#   coordinated-oauth:
#     type: streamable-http
#     url: https://mcp.example.com/mcp
#     requiresOAuth: true
#     # Stage rollout with coordination disabled (the default). Once EVERY replica is upgraded,
#     # pause MCP traffic and drain active refreshes/callbacks on EVERY replica before changing
#     # this flag. Apply the same value everywhere while paused, then resume. For rollback, drain,
#     # disable everywhere, replace the replicas, then resume. Do not toggle during live traffic.
#     # All coordinated replicas must use the same Redis cache.
#     oauthRefreshCoordination: false
#     # Peer refresh wait; capped at 30000 ms by the refresh execution budget.
#     oauthRefreshWaitTimeout: 15000
#     # Callback/adoption persistence wait; raise for longer publication budgets (max 840000 ms).
#     oauthPersistenceWaitTimeout: 15000
#     # When to ask users to sign in. `on_start` (default) asks when the turn starts. `on_use`
#     # waits for the agent's first call to one of this server's tools, but only when every tool
#     # the agent selected from it is deferred. Until a user signs in, tool search offers the
#     # tools listed in `oauthToolCatalog`; without one the turn-start prompt is kept.
#     # oauthPrompt: on_use
#     # oauthToolCatalog:
#     #   - name: read_sheet
#     #     description: Read the values in a spreadsheet range
#     #     inputSchema:
#     #       type: object
#     #       properties:
#     #         range: { type: string }
#     #       required: [range]
#   private-openid:
#     type: streamable-http
#     url: https://mcp.example.com/mcp
#     headers:
#       # Trusted operator configs automatically use the live session token and replace the
#       # connection once after a 401/403. A rejected tools/call is never replayed automatically.
#       # Enabled oauth or obo configuration takes precedence over this passthrough mode.
#       Authorization: "Bearer {{LIBRECHAT_OPENID_ACCESS_TOKEN}}"
#     # Sent only during a chat turn, merged over `headers` (these win on a duplicate name).
#     # Tool discovery has no conversation to resolve them against, so it omits them entirely:
#     # a `{{LIBRECHAT_BODY_*}}` placeholder here no longer hides the server's tool list.
#     requestHeaders:
#       X-Conversation-Id: "{{LIBRECHAT_BODY_CONVERSATIONID}}"
#   puppeteer:
#     type: stdio
#     command: npx
#     args:
#       - -y
#       - "@modelcontextprotocol/server-puppeteer"
#     timeout: 300000  # 5 minutes timeout for this server
#   filesystem:
#     # type: stdio
#     command: npx
#     args:
#       - -y
#       - "@modelcontextprotocol/server-filesystem"
#       - /home/user/LibreChat/
#     iconPath: /home/user/LibreChat/client/public/assets/logo.svg
#   mcp-obsidian:
#     command: npx
#     args:
#       - -y
#       - "mcp-obsidian"
#       - /path/to/obsidian/vault

# Definition of custom endpoints
endpoints:
  # (optional) How long the admin config catalog reuses a scope's model lists while its endpoint
  # config is unchanged, in milliseconds. Defaults to 120000 (two minutes), at most 3600000 (one
  # hour); 0 resolves them on every read (a fetched list may still come from the two-minute
  # model-list cache). Only librechat.yaml sets it.
  # catalogModelsTtlMs: 120000
  # assistants:
  #   disableBuilder: false # Disable Assistants Builder Interface by setting to `true`
  #   pollIntervalMs: 3000  # Polling interval for checking assistant updates
  #   timeoutMs: 180000  # Timeout for assistant operations
  #   # Should only be one or the other, either `supportedIds` or `excludedIds`
  #   supportedIds: ["asst_supportedAssistantId1", "asst_supportedAssistantId2"]
  #   # excludedIds: ["asst_excludedAssistantId"]
  #   # Only show assistants that the user created or that were created externally (e.g. in Assistants playground).
  #   # privateAssistants: false # Does not work with `supportedIds` or `excludedIds`
  #   # (optional) Models that support retrieval, will default to latest known OpenAI models that support the feature
  #   retrievalModels: ["gpt-4-turbo-preview"]
  #   # (optional) Assistant Capabilities available to all users. Omit the ones you wish to exclude. Defaults to list below.
  #   capabilities: ["code_interpreter", "retrieval", "actions", "tools", "image_vision"]
  # agents:
  #   # Maximum provider response-body inactivity for Agent model calls. Defaults to 15 minutes;
  #   # each received chunk resets the timer. Set to 0 to disable the idle timeout.
  #   modelResponseBodyTimeoutMs: 900000
  #   # Maximum wait for provider response headers. Defaults to 5 minutes; 0 disables.
  #   modelResponseHeadersTimeoutMs: 300000
  #   # Interval between keepalive comments on a chat stream that is quiet (for example while a
  #   # long tool runs), so proxies with an idle timeout (Cloudflare 100 s, nginx 60 s) keep it
  #   # open. Defaults to 25000 ms; 0 disables.
  #   streamKeepaliveIntervalMs: 25000
  #   # (optional) Default recursion depth for agents, defaults to 25
  #   recursionLimit: 50
  #   # Maximum provider error characters retained without content protection (0 hides detail).
  #   maxProviderErrorChars: 2000
  #   # (optional) Max recursion depth for agents, defaults to 25
  #   maxRecursionLimit: 100
  #   # (optional) Abort a run once a single streamed tool call's arguments exceed this many bytes.
  #   # Guards against runaway malformed tool-call generation. Defaults to 65536 (64 KiB); 0 disables.
  #   # Host-side skill/sandbox edits, not attached-worker edits. Over-budget calls write nothing.
  #   hostFileEdits:
  #     maxEdits: 100
  #     maxWorkBytes: 67108864  # cumulative matching/reconstruction bytes
  #     maxOccurrences: 100000 # cumulative occurrences across every edit/pass
  #     timeoutMs: 2000       # terminate an overlong worker job
  #     maxConcurrent: 2      # per API process; no waiting queue
  #   maxToolCallArgBytes: 65536
  #   # (optional) Abort a run once a single model generation emits more than this many stream events.
  #   # Defense in depth against looping provider streams. Disabled by default.
  #   maxDeltaEventsPerTurn: 100000
  #   # (optional) Per-tool overrides for maxToolCallArgBytes, keyed by tool name; 0 disables that
  #   # tool's guard. LibreChat ships { create_file: 131072 } so document-sized file writes are not
  #   # cut off; entries here merge over (and can replace) that default.
  #   maxToolCallArgBytesByTool:
  #     create_file: 131072
  #   # (optional) Disable the builder interface for agents
  #   disableBuilder: false
  #   # (optional) When conversation titles are generated:
  #   #   immediate (default): generate as soon as the request is made, in parallel
  #   #     with the response, from the user's first message (title appears within ~1-2s).
  #   #   final: defer generation until the full response completes (legacy behavior).
  #   # Set under `endpoints.all` instead to apply as the global default for all endpoints.
  #   titleTiming: immediate
  #   # (optional) Generate one-line headers for blocks of Agent reasoning and tool calls.
  #   # Header generation is a separate model call whose usage and cost are recorded.
  #   activityLabel: true
  #   activityEndpoint: openAI
  #   activityModel: gpt-4.1-nano
  #   # activityPrompt: 'Write a short activity label...'
  #   # activityMaxPerRun: 20
  #   # activityCharLimit: 600
  #   # (optional) Replace the generic Thinking/Thoughts heading with a live
  #   # generated orientation as sufficiently long top-level reasoning evolves.
  #   # Enabling this sends a bounded snapshot (up to 4,000 characters) of the
  #   # visible reasoning to the resolved label endpoint, which may be a different provider.
  #   # With Langfuse tracing enabled, that snapshot is also recorded as generation input
  #   # unless the active redaction policy suppresses the label call.
  #   # reasoningLabel: true
  #   # reasoningLabelModel: gpt-4.1-nano # falls back to activity/title/run model
  #   # reasoningLabelEndpoint: openAI    # falls back to activity/run endpoint
  #   # reasoningLabelPrompt: 'Describe the current reasoning direction...'
  #   # reasoningLabelMinChars: 500       # text required before the first label
  #   # reasoningLabelUpdateChars: 400    # new text between streaming revisions
  #   # reasoningLabelUpdateIntervalMs: 3000 # minimum time between streaming revisions
  #   # A final rewrite may run immediately after a meaningful 120-character tail.
  #   # reasoningLabelMaxPerRun: 8        # provider-call cap per response
  #   # (optional) Maximum total citations to include in agent responses, defaults to 30
  #   maxCitations: 30
  #   # (optional) Maximum citations per file to include in agent responses, defaults to 7
  #   maxCitationsPerFile: 7
  #   # (optional) Minimum relevance score for sources to be included in responses, defaults to 0.45 (45% relevance threshold)
  #   # Set to 0.0 to show all sources (no filtering), or higher like 0.7 for stricter filtering
  #   minRelevanceScore: 0.45
  #   # (optional) Maximum explicit subagents per agent, for both the flat list and
  #   # graph definitions. Defaults to 10; hard cap 50.
  #   maxSubagents: 20
  #   # (optional) Shared files during an active agent run. Each delegating agent must
  #   # also opt in with subagents.shareFiles. Inputs are read-only; outputs stay
  #   # private until explicitly published. Published files remain downloadable.
  #   # Live child activity, independent of the completed transcript.
  #   subagentActivity:
  #     replayTtlMs: 300000 # Increase for long silent tool calls.
  #     publicationTimeoutMs: 1000
  #     retryAttempts: 3
  #     retryBaseDelayMs: 100
  #     recoveryDelayMs: 1000
  #     memoryMaxStreams: 1000 # Non-Redis replay cache.
  #     memoryMaxBytes: 16777216
  #   fileSharing:
  #     enabled: false
  #     allowSiblingSharing: false # permit explicitly named sibling/descendant recipients
  #     maxFiles: 100 # manifest capacity, 1–1000
  #     maxPrivateBytes: 268435456 # aggregate private output snapshots, 256 MiB
  #     ttlMs: 3600000 # active manifest lifetime, at most 24 hours
  #   # (optional) Maximum concurrent Code API uploads per route and user. Defaults to 3.
  #   codeApiUploadConcurrency: 3
  #   # (optional) Maximum total time spent waiting on Code API rate limits. Defaults to 20000 ms.
  #   codeApiMaxRetryWaitMs: 20000
  #   # (optional) Cap the number of active accessible skills shown in the model-visible catalog.
  #   # Useful for large organizations where many department-specific skills may be available.
  #   skills:
  #     maxCatalogSkills: 20
  #   # (optional) Agent Capabilities available to all users. Omit the ones you wish to exclude. Defaults to list below.
  #   # web_search controls only LibreChat's external pipeline, not provider-native search.
  #   # Both require WEB_SEARCH.USE, seeded by interface.webSearch. See UPGRADING.md.
  #   capabilities: ["deferred_tools", "execute_code", "file_search", "web_search", "artifacts", "subagents", "actions", "context", "skills", "memory", "ask_user_question", "tools", "ocr"]
  #   # The following capabilities are opt-in and must be added explicitly:
  #   # "programmatic_tools", "stateful_code_sessions", "run_in_background", "tool_intents"
  #   # "stateful_code_sessions" is highly experimental and may change substantially.
  #   # (optional) Limit the workspace scopes users may select. Omit to allow all three.
  #   statefulCodeSessions:
  #     # Let new chats choose an attached machine from their agent's explicit machine allowlist.
  #     # On by default; only agents with a saved allowlist are affected. Set false to keep
  #     # every agent on its fixed machine (for example while older API replicas still run).
  #     allowEnvironmentSelection: true
  #     # Maximum additional machines per agent; default 32, supported ceiling 128.
  #     maxEnvironmentChoices: 32
  #     # Keep move-only behavior unless attach/detach is explicitly enabled.
  #     # Enable only after ALL API replicas run this build and advertise decision protocol 1
  #     # (CODE_ENVIRONMENT_DECISION_VERSION=1), then refresh clients.
  #     conversationMoves:
  #       enabled: true
  #       allowAttachDetach: false
  #     allowedEnvironments: ["user", "agent-user", "conversation"]
  #     # Personal BYOM enrollment. Requires allowPrincipalWorkers on a control plane.
  #     # Omitted values default to enabled and five registered environments per user.
  #     # Principal config overrides may tighten, but cannot raise, this ceiling.
  #     # Lowering the limit, or disabling enrollment, does not revoke existing machines.
  #     # This counts registered environments across control planes, not online workers.
  #     principalWorkers:
  #       enabled: true
  #       maxPerUser: 25
  #     # Route an agent to an operator-managed Code API or to a Code API whose
  #     # `remote-bridge` backend leases work to an outbound @librechat/code worker.
  #     environments:
  #       - id: managed-default
  #         name: Managed Code API
  #         type: managed
  #         baseURL: https://code.example.com/v1
  #         default: true
  #       - id: engineering-vm
  #         name: Engineering VM
  #         type: attached
  #         baseURL: https://code-bridge.example.com/v1
  #         # Pins an administrator-managed environment to one worker.
  #         owner: deployment
  #         pairing:
  #           workerId: engineering-vm
  #           tokenEnv: CODE_BRIDGE_ADMIN_TOKEN
  #       - id: personal-workers
  #         name: Personal Code Workers
  #         type: attached
  #         baseURL: https://code-bridge.example.com/v1
  #         # Lets authenticated users create principal-bound environments and
  #         # receive a one-time code for an outbound @librechat/code worker.
  #         # The administrator secret stays in the named environment variable.
  #         owner: deployment
  #         # Optionally expose only these bounded preferences to environment owners.
  #         configSchema:
  #           limits:
  #             # Maximum Bash execution budget the model may request per call.
  #             # Omit to preserve the historical 30-second limit. Hard cap: 300000.
  #             maxCommandTimeoutMs: 120000
  #             # Foreground Bash default when timeoutMs is omitted. Omit to keep 30000.
  #             # Clamped to the effective admin, worker, and verified HTTP ceilings.
  #             # Background calls still default to the effective maximum.
  #             # Programmatic Bash uses this only when timeout is omitted; explicit
  #             # values keep the same negotiated ceiling. Its SDK has a 1000 ms floor
  #             # and cannot run under a smaller ceiling; use bash_tool for those budgets.
  #             # defaultCommandTimeoutMs: 60000
  #             # Attached read_file window when max_lines is omitted. Omit to keep 200.
  #             # Valid range: 1–500 lines; the existing byte budget still applies.
  #             # defaultReadFileLines: 500
  #             # New strict fields require all LibreChat API replicas to be updated first.
  #             # Optional total HTTP budget per workspace tool call, including
  #             # admission, retries, worst-case execution, settlement, and delivery.
  #             # Do NOT enable until every LibreChat API replica recognizes this
  #             # strict config field, Code API honors X-LibreChat-Workspace-Queue-Wait-Ms,
  #             # and a non-mutating timed canary verifies the live CDN, load balancer,
  #             # ingress, and caller can all outlast this value. The Nginx example
  #             # (120s) cannot establish the live limit. Omission keeps 30s admission.
  #             # With 125s total, a read can queue <=90s, a default command <=85s,
  #             # a 90s command <=25s. With the default 10s admission reserve,
  #             # commands >105s cannot fit; the 120s command ceiling above requires
  #             # a VERIFIED total budget of at least 140s to be usable.
  #             # maxRequestTimeoutMs: 125000
  #             # Optional command admission allowance before local dispatch overhead.
  #             # Omission reserves 10s; valid range: 1000–300000 ms. The HTTP budget
  #             # must exceed this allowance plus 10s settlement/delivery grace;
  #             # with the 10s default, a budget of 20s or less is rejected.
  #             # Smaller allowances give a busy worker less time to accept the call.
  #             # minCommandAdmissionMs: 10000
  #           permissions:
  #             fileWrite:
  #               allowed: [allow, ask, deny]
  #               default: ask
  #             commandExecution:
  #               # Add allow to offer Full access in the chat composer. Both
  #               # permission categories must permit allow; defaults can stay ask.
  #               # Full access skips routine code prompts within the worker sandbox.
  #               # Explicit endpoint ask/deny rules and hooks still apply.
  #               allowed: [ask, deny]
  #               default: ask
  #         pairing:
  #           allowPrincipalWorkers: true
  #           tokenEnv: CODE_BRIDGE_ADMIN_TOKEN
  #   # (optional) Trusted origin for internal event delivery. By default, LibreChat
  #   # uses its own bound listener; override only for an internal TLS/front-door route.
  #   eventDriven:
  #     # selfUrl: 'https://librechat.internal'
  #   # (optional) Automatic conversational delivery for supported completed background tasks.
  #   # Enabled by default; set false to keep background tools and subagents poll-only.
  #   backgroundTasks:
  #     completionWakeups: true
  #     # Deliver a conversation's ready results together in one wake-up. On by default; set false
  #     # during a rolling upgrade while replicas from releases without it still serve traffic.
  #     completionReceiptBatching: true
  #     # Allow owners to cooperatively cancel ordinary background tools, including BYOM Bash.
  #     ordinaryToolCancellation: false
  #   # (optional) Show a conversation's pull request in the chat header and the sidebar. It is on
  #   # as soon as the server has a GitHub token and a repository scope, with no switch needed:
  #   # the token is `token` below, else the first of GITHUB_PULL_REQUEST_TOKEN, GITHUB_TOKEN and
  #   # GH_TOKEN that is set, and the scope is `allowedRepositories` or `allowAllRepositories`.
  #   # Without either, every chat simply shows no pull request. It also needs a code worker built
  #   # from LibreChat-AI/code-interpreter#311 or later that reports its branch, with
  #   # CODEAPI_BRIDGE_LANE_GIT=true set on the Code API. Use a fine-grained token limited to the
  #   # repositories involved, with read-only "Pull requests", "Checks" and "Contents" permissions.
  #   # Without "Checks" every matched pull request fails to load, and without "Contents" a chat
  #   # whose branch has moved on since its last command does.
  #   # On GitLab the fallbacks are GITLAB_PULL_REQUEST_TOKEN and GITLAB_TOKEN, and the token needs
  #   # read_api; on Bitbucket the fallback is BITBUCKET_PULL_REQUEST_TOKEN. Repositories may be
  #   # nested GitLab group paths such as group/sub/name or group/sub/*.
  #   pullRequests:
  #     enabled: true # set false to turn the feature off
  #     # github (default), gitlab, or bitbucket (Bitbucket Cloud). Read from this file only.
  #     # provider: "gitlab"
  #     # GitHub Enterprise Server, a *.ghe.com tenant, or a self-managed GitLab host; the
  #     # provider's own host (github.com, gitlab.com, bitbucket.org) when omitted.
  #     # host: "github.example.com"
  #     # Environment variable reference only, never the token itself. Optional, see above.
  #     token: "${GITHUB_PULL_REQUEST_TOKEN}"
  #     # Let each user connect their own account, so lookups use their token, rate limit and
  #     # repository access instead of the server's (read from this file only). Register
  #     # <DOMAIN_SERVER>/api/pull-requests/oauth/callback as the app's callback URL. On GitHub a
  #     # GitHub App with read-only Pull requests, Checks and Contents permissions is recommended.
  #     # Changing clientId, provider or host asks users to connect again; a changed scope only
  #     # applies to new connections. Disconnecting removes every grant of the user.
  #     # oauth:
  #     #   clientId: "${GITHUB_PR_OAUTH_CLIENT_ID}"
  #     #   clientSecret: "${GITHUB_PR_OAUTH_CLIENT_SECRET}"
  #     #   scope: "repo" # only for a classic OAuth app; GitLab defaults to read_api
  #     #   flowTimeoutMinutes: 10 # time to approve at the provider
  #     #   requestTimeoutSeconds: 10 # per code exchange or token refresh
  #     #   retentionDays: 180 # an unused connection is removed after this; each use extends it
  #     # Repositories the token may be used for, as owner/name or owner/*. A worker reports its
  #     # own repository, and only these are ever looked up with the server's token.
  #     allowedRepositories: ["LibreChat-AI/LibreChat"]
  #     # Or look up every repository a worker reports, limited only by what the token can read.
  #     # Off by default: any user could then point the server's token at any repository it can
  #     # see, so use a read-only token scoped to the repositories you are willing to show.
  #     allowAllRepositories: false
  #     # Seconds a looked-up pull request is reused before GitHub is asked again (5 to 3600).
  #     cacheTtlSeconds: 30
  #     # Results cached per credential before the oldest is evicted (10 to 100000). Raise it when many
  #     # repositories and branches are active at once, or fresh results are evicted and GitHub is asked again.
  #     cacheMaxEntries: 500
  #     # Credentials cached at once (1 to 10000), deployment-wide; the one idle longest is dropped
  #     # past it. When principals configure different values, the largest applies.
  #     cacheMaxCredentials: 256
  #     # Lookups one sidebar request runs at once (1 to 16); each is a few GitHub requests.
  #     maxConcurrentLookups: 4
  #     # Seconds one sidebar request may stay open in total (1 to 120); entries still waiting then
  #     # answer with an upstream error and the row shows nothing until the next refresh.
  #     batchTimeoutSeconds: 20
  #     # Bounds on one lookup. A repository with many check runs reads one page of 100 per request.
  #     requestTimeoutSeconds: 10 # longest single GitHub request (1 to 60)
  #     lookupTimeoutSeconds: 30 # longest the whole lookup may take (1 to 120)
  #     maxCheckRunPages: 10 # pages read before checks are reported as running (1 to 50)
  #     maxCandidatePullRequests: 10 # pull requests listed per state when matching a reused branch (1 to 100)
  #     maxCandidatePages: 1 # pages of those read per state, for branch names reused more often (1 to 10)
  #     maxHeadComparisons: 3 # candidates compared with the chat's last commit (0 to 20)
  #     # Share looked-up pull requests and GitHub rate limit cooldowns between replicas, so they
  #     # do not each spend the token on the same answer. Only takes effect with USE_REDIS. Failed
  #     # lookups are never shared.
  #     sharedCache: false
  #     # Milliseconds one shared cache call may take before a lookup carries on without it (10 to 5000).
  #     sharedCacheTimeoutMs: 250
  #     # Redis keys the shared cache uses at most, for results and again for rate limits (64 to
  #     # 1000000). Read from this file only.
  #     sharedCacheSlots: 65536
  #   # "run_in_background" makes Code Interpreter tools eligible by default and enables per-tool MCP opt-in.
  #   # "tool_intents" enables live model-written labels for native tools and opted-in MCP tools.
  #   # (optional) Require user approval before matching tool calls. Disabled by default.
  #   toolApproval:
  #     # Opt in after all replicas have been upgraded. Agent tool rows then expose
  #     # Always ask, Always approve, Ask once per chat, and Ask once then always approve.
  #     # Explicit administrator ask/deny rules and hooks remain authoritative.
  #     agentModes: false
  #     grantLookupTimeoutMs: 3000
  #     enabled: true
  #     mode: default # default, dontAsk, or bypass
  #     allow: ["mcp:trusted-server:read_*"]
  #     deny: ["mcp:*:delete_*"] # Deny rules always take precedence
  #     ask: ["mcp:*:*"]
  #     reason: "Review {tool} before it runs."
  #     allowAlways: false # Offer "Always allow" to stop prompting for a tool for the rest of a conversation
  #   # (optional) Persist Agent runs paused for approval or Ask User. MongoDB is the durable default.
  #   checkpointer:
  #     type: mongo # mongo (default) or memory (single-process development only)
  #     ttl: 86400 # Approval window in seconds; defaults to 24 hours
  #   # (optional) Keep the user's answers to Ask User questions in the model context verbatim,
  #   # even after the messages that carried them were summarized or pruned. On by default.
  #   askUserQuestion:
  #     retainedAnswers:
  #       enabled: true
  #       maxTokens: 4096 # Older answers drop first past this budget; the newest is always kept
  #   # (optional) Authenticate machine clients for the Agent Management API.
  #   # Each verified OAuth client is bound server-side to one existing LibreChat
  #   # user and tenant; that user's normal role and Agent ACLs still apply.
  #   managementApi:
  #     auth:
  #       oidc:
  #         enabled: true
  #         issuer: 'https://identity.example.com/'
  #         audience: 'https://librechat.example.com/agents'
  #         # jwksUri: 'https://identity.example.com/.well-known/jwks.json'
  #         # Cognito M2M access tokens use client_id instead of aud. For that
  #         # profile, omit audience and require the access-token type and scope:
  #         # tokenUse: access
  #         # requiredScopes: ['agents-api/manage']
  #       clients:
  #         - clientId: 'machine-client-id'
  #           # subject: 'provider-specific-service-principal-subject'
  #           userId: '507f1f77bcf86cd799439011'
  #           tenantId: 'tenant-id'

  # (optional) Title settings under `endpoints.all` apply to every endpoint one field at a
  # time: a field set here wins over the endpoint's own value, and a field left out keeps it.
  # `titleEndpoint` and `titleModel` are one choice, taken together from the first of `all`,
  # the endpoint's block, or its custom endpoint entry that sets either.
  # all:
  #   titleConvo: true
  #   titleMethod: completion

  # (optional) Custom request headers for the built-in OpenAI / Google endpoints.
  # Forwarded on every request to the provider (or an AI gateway / reverse proxy
  # in front of it) while keeping provider-native request shaping intact. Values
  # support env vars (${VAR}), user fields ({{LIBRECHAT_USER_*}}), and request-body
  # fields ({{LIBRECHAT_BODY_CONVERSATIONID}}). Set the same `headers:` block under
  # `endpoints.all` to apply globally across endpoints (endpoint values win on key
  # collisions). NOTE: send metadata headers like these only behind a gateway that
  # consumes them — native provider APIs ignore unknown headers.
  # openAI:
  #   headers:
  #     cf-aig-metadata: '{"user_email":"{{LIBRECHAT_USER_EMAIL}}","app":"librechat"}'
  # google:
  #   headers:
  #     cf-aig-metadata: '{"user_email":"{{LIBRECHAT_USER_EMAIL}}","app":"librechat"}'

  # Anthropic endpoint configuration with Vertex AI support
  # Use this to run Anthropic Claude models through Google Cloud Vertex AI
  # anthropic:
  #   # (optional) Override the adaptive stream-smoothing cadence in milliseconds.
  #   # Agents SDK-backed providers smooth at 25ms by default; set 0 to disable
  #   # smoothing. (Legacy Assistants/Ollama paths sleep this long per chunk instead.)
  #   streamRate: 20
  #   # (optional) Title model for conversation titles
  #   titleModel: claude-3.5-haiku  # Use the visible model name (key from models config)
  #   # (optional) Custom request headers, same placeholder resolution as above.
  #   # Useful for correlating reverse-proxied requests by conversation, since an
  #   # unknown header is simply ignored by the native Anthropic API.
  #   headers:
  #     cf-aig-metadata: '{"user_email":"{{LIBRECHAT_USER_EMAIL}}","app":"librechat"}'
  #     X-Conversation-Id: '{{LIBRECHAT_BODY_CONVERSATIONID}}'
  #
  #   # Vertex AI Configuration - enables running Claude models via Google Cloud
  #   # This is similar to Azure OpenAI but for Anthropic models on Google Cloud
  #   # Vertex AI is automatically enabled when this config section is present
  #   vertex:
  #     # Vertex AI region (optional, defaults to 'us-east5')
  #     # Available regions: us-east5, us-central1, europe-west1, europe-west4, asia-southeast1
  #     # Multi-region endpoints: us, eu, global
  #     # IMPORTANT: specific regional endpoints only serve Claude Sonnet 4.6 and earlier. Newer
  #     # models (Opus 4.7+, Opus 5, Sonnet 5, Fable 5/5.1) require "global" or a multi-region value
  #     # ("us"/"eu") and will 404 on a specific region. "global" also avoids the 10% regional premium.
  #     region: "us-east5"
  #     # Path to Google service account key file (optional)
  #     # If not specified, uses GOOGLE_SERVICE_KEY_FILE env var or default path (api/data/auth.json)
  #     # The project_id is automatically extracted from the service key file
  #     # serviceKeyFile: "/path/to/service-account.json"
  #     # Google Cloud Project ID (optional) - auto-detected from service key file
  #     # Only specify if you need to override the project_id in your service key
  #     # projectId: "${VERTEX_PROJECT_ID}"
  #
  #     # ============================================================================
  #     # Model Configuration - Set Visible Model Names and Deployment Mappings
  #     # Similar to Azure OpenAI model naming pattern
  #     # ============================================================================
  #
  #     # Option 1: Simple array (legacy format - model name = deployment name)
  #     # Use this if you want the technical model IDs to show in the UI
  #     # models:
  #     #   - "claude-fable-5-1"
  #     #   - "claude-fable-5"
  #     #   - "claude-opus-5"
  #     #   - "claude-opus-4-8"
  #     #   - "claude-sonnet-4-6"
  #     #   - "claude-3-7-sonnet-20250219"
  #     #   - "claude-3-5-sonnet-v2@20241022"
  #     #   - "claude-3-5-haiku@20241022"
  #
  #     # Option 2: Object format with custom visible names (RECOMMENDED)
  #     # The key is the visible model name shown in the UI (can be any name you want)
  #     # The deploymentName is the actual Vertex AI model ID used for API calls
  #     # You can use friendly names (avoid spaces for cleaner YAML) or technical IDs as keys
  #     models:
  #       claude-fable-5.1:
  #         deploymentName: claude-fable-5-1
  #       claude-fable-5:
  #         deploymentName: claude-fable-5
  #       claude-opus-5:
  #         deploymentName: claude-opus-5
  #       claude-opus-4.8:
  #         deploymentName: claude-opus-4-8
  #       claude-opus-4.5:
  #         deploymentName: claude-opus-4-5@20251101
  #       claude-sonnet-4:
  #         deploymentName: claude-sonnet-4-6
  #       claude-3.7-sonnet:
  #         deploymentName: claude-3-7-sonnet-20250219
  #       claude-3.5-sonnet:
  #         deploymentName: claude-3-5-sonnet-v2@20241022
  #       claude-3.5-haiku:
  #         deploymentName: claude-3-5-haiku@20241022
  #
  #     # Option 3: Mixed format with default deploymentName
  #     # Set a default deploymentName and use boolean values for models
  #     # deploymentName: claude-sonnet-4-6
  #     # models:
  #     #   claude-sonnet-4: true  # Will use the default deploymentName
  #     #   claude-3.5-haiku:
  #     #     deploymentName: claude-3-5-haiku@20241022  # Override for this model

  custom:
    # xAI: Grok 4.7 uses the existing OpenAI-compatible chat and agent paths.
    # https://docs.x.ai/developers/grok-4-7
    # Set XAI_API_KEY in your environment. No separate SpaceXAI provider is needed.
    - name: 'xai'
      # Optional: expose this endpoint only to users in the named tenant.
      # tenantId: 'your-tenant-id'
      apiKey: '${XAI_API_KEY}'
      baseURL: 'https://api.x.ai/v1'
      models:
        default: ['grok-4.7']
        fetch: true
      titleConvo: true
      titleModel: 'grok-4.7'
      modelDisplayLabel: 'xAI'

    # Anthropic-compatible Example (native `/v1/messages` API)
    # Set `provider: anthropic` to use the native Anthropic client instead of the
    # default OpenAI-compatible one — for Anthropic itself or Anthropic-compatible
    # gateways (e.g. AI gateways, OpenCode Zen). The `baseURL` must be the API root
    # the Anthropic SDK appends `/v1/messages` to. List models explicitly: model
    # auto-fetch uses the OpenAI `/models` convention and is not used for this provider.
    - name: 'Claude-Compatible'
      provider: 'anthropic'
      apiKey: '${ANTHROPIC_API_KEY}'
      baseURL: 'https://api.anthropic.com'
      # (optional) headers forwarded on every request (e.g. for a reverse proxy);
      # values support the same placeholders as built-in endpoints.
      headers:
        anthropic-version: '2023-06-01'
      models:
        default:
          - 'claude-sonnet-4-5'
          - 'claude-opus-4-5'
        fetch: false
      titleConvo: true
      titleModel: 'claude-sonnet-4-5'
      # Agent activity groups: collapse each block of reasoning + tool calls
      # under a generated one-line header. Same shape as the title options.
      activityLabel: true
      activityModel: 'claude-3-5-haiku'
      # activityEndpoint: 'anthropic'   # run labels on another endpoint's credentials
      # activityPrompt: 'Write a 5-9 word past-tense label...'
      # activityMaxPerRun: 20           # cost cap per response
      # activityCharLimit: 600          # per-entry prompt truncation
      # Parent phase summaries are an independent opt-in. They collapse 2+
      # logical activities before the answer into one run-level summary.
      # activityPhaseLabel: true
      # activityPhaseModel: 'claude-3-5-haiku' # falls back to activity/title/run model
      # activityPhaseEndpoint: 'anthropic'     # falls back to activity/run endpoint
      # activityPhasePrompt: 'Summarize the completed agent phase...'
      # activityPhaseMaxPerRun: 5               # cost cap per response
      # Live reasoning labels are also independent. They update one top-level
      # THINK heading in place and never create or shift message content parts.
      # Enabling this sends a bounded snapshot (up to 4,000 characters) of the
      # visible reasoning to the resolved label endpoint, which may be a different provider.
      # With Langfuse tracing enabled, that snapshot is also recorded as generation input
      # unless the active redaction policy suppresses the label call.
      # reasoningLabel: true
      # reasoningLabelModel: 'claude-3-5-haiku' # falls back to activity/title/run model
      # reasoningLabelEndpoint: 'anthropic'     # falls back to activity/run endpoint
      # reasoningLabelPrompt: 'Describe the current reasoning direction...'
      # reasoningLabelMinChars: 500
      # reasoningLabelUpdateChars: 400
      # reasoningLabelUpdateIntervalMs: 3000
      # A final rewrite may run immediately after a meaningful 120-character tail.
      # reasoningLabelMaxPerRun: 8
      modelDisplayLabel: 'Claude (Compatible)'

    # Groq Example
    - name: 'groq'
      apiKey: '${GROQ_API_KEY}'
      baseURL: 'https://api.groq.com/openai/v1/'
      models:
        default:
          - 'llama3-70b-8192'
          - 'llama3-8b-8192'
          - 'llama2-70b-4096'
          - 'mixtral-8x7b-32768'
          - 'gemma-7b-it'
        fetch: false
      titleConvo: true
      titleModel: 'mixtral-8x7b-32768'
      modelDisplayLabel: 'groq'

    # Mistral AI Example
    - name: 'Mistral' # Unique name for the endpoint
      # For `apiKey` and `baseURL`, you can use environment variables that you define.
      # recommended environment variables:
      apiKey: '${MISTRAL_API_KEY}'
      baseURL: 'https://api.mistral.ai/v1'

      # Models configuration
      models:
        # List of default models to use. At least one value is required.
        default: ['mistral-tiny', 'mistral-small', 'mistral-medium']
        # Fetch option: Set to true to fetch models from API.
        fetch: true # Defaults to false.

      # Optional configurations

      # Title Conversation setting
      titleConvo: true # Set to true to enable title conversation

      # Title Method: Choose between "completion" or "functions".
      # titleMethod: "completion"  # Defaults to "completion" if omitted.

      # Title Model: Specify the model to use for titles.
      titleModel: 'mistral-tiny' # Defaults to "gpt-3.5-turbo" if omitted.

      # Summarize setting: Set to true to enable summarization.
      # summarize: false

      # Summary Model: Specify the model to use if summarization is enabled.
      # summaryModel: "mistral-tiny"  # Defaults to "gpt-3.5-turbo" if omitted.

      # The label displayed for the AI model in messages.
      modelDisplayLabel: 'Mistral' # Default is "AI" when not set.

      # Add additional parameters to the request. Default params will be overwritten.
      # addParams:
      # safe_prompt: true # This field is specific to Mistral AI: https://docs.mistral.ai/api/

      # Drop Default params parameters from the request. See default params in guide linked below.
      # NOTE: For Mistral, it is necessary to drop the following parameters or you will encounter a 422 Error:
      dropParams: ['stop', 'user', 'frequency_penalty', 'presence_penalty']

    # OpenRouter Example
    - name: 'OpenRouter'
      # For `apiKey` and `baseURL`, you can use environment variables that you define.
      # recommended environment variables:
      apiKey: '${OPENROUTER_KEY}'
      baseURL: 'https://openrouter.ai/api/v1'
      headers:
        x-librechat-body-parentmessageid: '{{LIBRECHAT_BODY_PARENTMESSAGEID}}'
      models:
        default: ['meta-llama/llama-3.3-70b-instruct']
        fetch: true
      titleConvo: true
      titleModel: 'meta-llama/llama-3.3-70b-instruct'
      # Recommended: Drop the stop parameter from the request as Openrouter models use a variety of stop tokens.
      dropParams: ['stop']
      modelDisplayLabel: 'OpenRouter'

  # AWS Bedrock Example
  # Note: Bedrock endpoint is configured via environment variables
  # bedrock:
  #   # Models Configuration
  #   # Specify which models are available (equivalent to BEDROCK_AWS_MODELS env variable)
  #   models:
  #     - "anthropic.claude-3-7-sonnet-20250219-v1:0"
  #     - "anthropic.claude-3-5-sonnet-20241022-v2:0"
  #
  #   # Inference Profiles Configuration
  #   # Maps model IDs to their inference profile ARNs
  #   # IMPORTANT: The model ID (key) MUST be a valid AWS Bedrock model ID that you've added to the models list above
  #   # The ARN (value) is the inference profile you wish to map to for that model
  #   # Both the model ID and ARN are sent to AWS - the model ID for validation/metadata, the ARN for routing
  #   inferenceProfiles:
  #     "us.anthropic.claude-sonnet-4-6": "${BEDROCK_INFERENCE_PROFILE_CLAUDE_SONNET}"
  #     "anthropic.claude-3-7-sonnet-20250219-v1:0": "arn:aws:bedrock:us-west-2:123456789012:application-inference-profile/abc123"
  #
  #   # Guardrail Configuration
  #   guardrailConfig:
  #     guardrailIdentifier: "your-guardrail-id"
  #     guardrailVersion: "1"
  #
  #     # Trace behavior for debugging (optional)
  #     # - "enabled": Include basic trace information about guardrail assessments
  #     # - "enabled_full": Include comprehensive trace details (recommended for debugging)
  #     # - "disabled": No trace information (default)
  #     # Trace output is logged to application log files for compliance auditing
  #     trace: "enabled"
# Example modelSpecs configuration showing grouping options
# The 'group' field organizes model specs in the UI selector:
# - If 'group' matches an endpoint name (e.g., "openAI", "groq"), the spec appears nested under that endpoint
# - If 'group' is a custom name (doesn't match any endpoint), it creates a separate collapsible section
# - If 'group' is omitted, the spec appears as a standalone item at the top level
#
# The 'groupIcon' field sets an icon for custom groups:
# - Only needs to be set on one spec per group (first one is used)
# - Can be a URL or a built-in endpoint key (e.g., "openAI", "anthropic", "groq")
# modelSpecs:
#   list:
#     # Example 1: Nested under an endpoint (grouped with openAI endpoint)
#     - name: "gpt-4o"
#       label: "GPT-4 Optimized"
#       description: "Most capable GPT-4 model with multimodal support"
#       # default: true      # Hard admin default; takes precedence over prior user choices
#       # softDefault: true  # First-time default only; skipped after a user selects a model/spec/agent
#       # showInMenu: false  # Hide from the model selector while keeping explicit `spec` access
#       group: "openAI"  # String value matching the endpoint name
#       preset:
#         endpoint: "openAI"
#         model: "gpt-4o"
#       # Skills can be enabled per model spec. Use true for the user's active
#       # accessible skill catalog, false to force skills off, or a name list as
#       # a strict allowlist for catalog, manual, and always-apply resolution.
#       # skills: ["brand-guidelines", "code-review"]
#       # Subagents can be enabled per model spec. `allowSelf: true` lets the
#       # ephemeral agent spawn a fresh isolated copy of itself for focused work.
#       # subagents:
#       #   enabled: true
#       #   allowSelf: true
#       #   agent_ids: []
#
#     # Example 2: Nested under a custom endpoint (grouped with groq endpoint)
#     - name: "llama3-70b-8192"
#       label: "Llama 3 70B"
#       description: "Fastest inference available - great for quick responses"
#       group: "groq"  # String value matching your custom endpoint name from endpoints.custom
#       preset:
#         endpoint: "groq"
#         model: "llama3-70b-8192"
#
#     # Example 3: Custom group with icon (creates a separate collapsible section)
#     - name: "coding-assistant"
#       label: "Coding Assistant"
#       description: "Specialized for coding tasks"
#       group: "my-assistants"  # Custom string - doesn't match any endpoint, so creates its own group
#       groupIcon: "https://example.com/icons/assistants.png"  # Icon URL for the group
#       preset:
#         endpoint: "openAI"
#         model: "gpt-4o"
#         instructions: "You are an expert coding assistant..."
#         temperature: 0.3
#
#     - name: "writing-assistant"
#       label: "Writing Assistant"
#       description: "Specialized for creative writing"
#       group: "my-assistants"  # Same custom group name - both specs appear in same section
#       # No need to set groupIcon again - the first spec's icon is used
#       preset:
#         endpoint: "anthropic"
#         model: "claude-sonnet-4"
#         instructions: "You are a creative writing expert..."
#
#     # Example 4: Custom group using built-in icon key
#     - name: "fast-models"
#       label: "Fast Response Model"
#       group: "Fast Models"
#       groupIcon: "groq"  # Uses the built-in Groq icon
#       preset:
#         endpoint: "groq"
#         model: "llama3-8b-8192"
#
#     # Example 5: Standalone (no group - appears at top level)
#     - name: "general-assistant"
#       label: "General Assistant"
#       description: "General purpose assistant"
#       # No 'group' field - appears as standalone item at top level (not nested)
#       # hideBadgeRow: true  # Optional: hides the tool badge row for this spec
#       preset:
#         endpoint: "openAI"
#         model: "gpt-4o-mini"

# Automatic conversation summarization (optional)
# summarization:
#   enabled: true
#   provider: "openAI"
#   model: "gpt-4o-mini"
#   retainRecent:
#     turns: 2 # Keep the newest complete user/assistant turns outside the summary
#     tokens: 2000 # Also preserve up to this many recent tokens

# fileConfig:
#   skills:
#     # Bound parallel storage deletes after a failed archive import (default: 8).
#     # Set to 1 for serial cleanup on storage backends that require it.
#     importCleanupConcurrency: 8
#   # Store best-effort text for inferred tool-routed message attachments. On each turn,
#   # deliver it only if no available tool can read the type. Off by default; also configurable
#   # under endpoints.default or a provider/custom endpoint name. Explicit destinations stand.
#   # Existing files without extracted text are not backfilled. Paused runs retain encoded text
#   # and conservatively count referenced fallback text against current limits on resume.
#   textFallbackWithoutTools: false
#   fileContextSizeLimit: 128  # Maximum aggregate model-bound attachment size in one agent turn (MB)
#   fileContextCharLimit: 1000000  # Maximum aggregate extracted-text characters in one agent turn
#   endpoints:
#     agents:
#       fileLimit: 10
#     assistants:
#       fileLimit: 5
#       fileSizeLimit: 10  # Maximum size for an individual file in MB
#       totalSizeLimit: 50  # Maximum total size for all files in a single request in MB
#       supportedMimeTypes:
#         - "image/.*"
#         - "application/pdf"
#     openAI:
#       disabled: true  # Disables file uploading to the OpenAI endpoint
#     default:
#       totalSizeLimit: 20
#     YourCustomEndpointName:
#       fileLimit: 2
#       fileSizeLimit: 5
#   serverFileSizeLimit: 100  # Global server file size limit in MB
#   avatarSizeLimit: 2  # Limit for user avatar image size in MB
#   imageGeneration: # Image Gen settings, either percentage or px
#     percentage: 100
#     px: 1024
#   # Client-side image resizing to prevent upload errors
#   # Users can toggle this in Settings > Chat. Setting `enabled` here overrides
#   # that choice for everyone and locks the toggle; omit it to leave users in control.
#   clientImageResize:
#     enabled: false  # Force resizing on (true) or off (false) for everyone; omit it and each user decides, with resizing on by default
#     maxWidth: 1900  # Maximum width for resized images (default: 1900)
#     maxHeight: 1900  # Maximum height for resized images (default: 1900)
#     quality: 0.92  # JPEG quality for compression (0.0-1.0, default: 0.92)
# # See the Custom Configuration Guide for more information on Assistants Config:
# # https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/assistants_endpoint

# Web Search Configuration (optional)
# Keys and URLs are usually `${ENV_VAR}` references. A literal value, or a key saved
# through the admin config API (encrypted at rest), is used as a system credential.
# A key reaches a URL written in config only when both are set in the same place
# (this file, or one admin config profile), and a later profile that changes, blanks
# or removes that URL without storing the key again drops it. An environment key or
# a user's own key never reaches a URL written in config. Reference both from the
# environment, or set both together. The admin config API asks for a stored key
# again when a write changes or removes the URL beside it.
# webSearch:
#   # Jina Reranking Configuration
#   jinaApiKey: '${JINA_API_KEY}'  # Your Jina API key
#   jinaApiUrl: '${JINA_API_URL}'  # Custom Jina API URL (optional, defaults to https://api.jina.ai/v1/rerank)
#   # Other rerankers
#   cohereApiKey: '${COHERE_API_KEY}'
#   # Search providers
#   serperApiKey: '${SERPER_API_KEY}'
#   searxngInstanceUrl: '${SEARXNG_INSTANCE_URL}'
#   searxngApiKey: '${SEARXNG_API_KEY}'
#   # Tavily (search provider and/or scraper)
#   tavilyApiKey: '${TAVILY_API_KEY}'
#   # Keenable (search provider; keyless by default, a key only lifts rate limits)
#   keenableApiKey: '${KEENABLE_API_KEY}'
#   # Content scrapers
#   firecrawlApiKey: '${FIRECRAWL_API_KEY}'
#   firecrawlApiUrl: '${FIRECRAWL_API_URL}'
#   # Outbound search and scrape requests are validated at connect time against
#   # their resolved IP and blocked from reaching private, loopback, link-local,
#   # or cloud-metadata space. `allowedAddresses` is an SSRF exemption list, NOT a
#   # strict whitelist: hostname/IP + port pairs listed here bypass that block for
#   # one deliberately-private endpoint (for example a self-hosted SearXNG
#   # instance); public destinations continue to work normally.
#   #
#   # Entries must include a port: `host:port`, `private.ip:port`, or `[ipv6]:port`.
#   # Do not use URLs, paths, CIDR ranges, bare hosts/IPs, or public IP literals.
#   # A hostname entry trusts whatever IP that name resolves to on the listed port,
#   # so only list hosts you fully control and whose DNS cannot be repointed by an
#   # attacker. Listing an attacker-controllable or DNS-rebindable host re-opens the
#   # private-address path this guard closes. Prefer literal IPs where you can.
#   #
#   # Self-hosted endpoints need an entry. A private destination such as
#   # `http://searxng:8080`, `http://firecrawl:3002`, or `http://127.0.0.1:8080` is
#   # blocked once this guard is active, so list it here or those requests will fail.
#   #
#   # A proxy from `HTTP_PROXY`, `HTTPS_PROXY`, or `ALL_PROXY` (either case) is
#   # exempted automatically and needs no entry. That exemption is applied to the
#   # whole tool rather than per destination, so a host `NO_PROXY` sends direct also
#   # carries it. Note that when a proxy carries the request the proxy resolves the
#   # destination, so destination egress policy is the proxy's to enforce, and for
#   # https targets the proxy's own tunnel replaces this guard entirely.
#   # allowedAddresses:
#   #   - 'searxng:8080'
#   #   - '127.0.0.1:8080'
#
# Tavily as both search and scraper provider example:
# webSearch:
#   searchProvider: tavily
#   scraperProvider: tavily
#   tavilyApiKey: '${TAVILY_API_KEY}'
#   # Optional: custom API URLs (defaults to https://api.tavily.com/search and https://api.tavily.com/extract)
#   # tavilySearchUrl: '${TAVILY_SEARCH_URL}'
#   # tavilyExtractUrl: '${TAVILY_EXTRACT_URL}'
#   tavilySearchOptions:
#     searchDepth: basic        # 'basic', 'advanced', 'fast', or 'ultra-fast' (default: basic)
#     maxResults: 5             # 1-20 results per search (default: 5)
#     topic: general            # 'general', 'news', or 'finance'
#     # includeAnswer: basic    # Include answer summary: true, 'basic', or 'advanced'
#     # includeRawContent: markdown # Include raw content: true, 'markdown', or 'text'
#     # includeImages: true     # Include images in results
#     # includeFavicon: true    # Include favicon URL for each result
#     # chunksPerSource: 3      # Chunks per source, only with 'advanced' depth (1-3)
#     # safeSearch: false       # Override Tavily safe_search filtering (true is enterprise-only)
#     # includeDomains:         # Restrict search to specific domains (max 300)
#     #   - 'example.com'
#     #   - 'docs.example.com'
#     # excludeDomains:         # Exclude specific domains from results (max 150)
#     #   - 'spam.com'
#     # timeRange: week         # 'day', 'week', 'month', or 'year'
#     # timeout: 15000          # HTTP request timeout in milliseconds (max 120000)
#   tavilyScraperOptions:
#     extractDepth: basic       # 'basic' (1 credit/5 URLs) or 'advanced' (2 credits/5 URLs, more thorough)
#     # includeImages: false    # Include images extracted from URLs
#     # includeFavicon: false   # Include favicon URL for each result
#     # format: markdown        # 'markdown' (default) or 'text' (plain text, may increase latency)
#     # timeout: 15000          # HTTP request timeout in milliseconds (max 120000); Tavily Extract receives seconds clamped to 1-60
#
# Keenable as both search provider and scraper example — a fully keyless web
# search stack: no API key for any of the three categories. The public search and
# fetch endpoints are rate-limited; a key only lifts the cap.
# webSearch:
#   searchProvider: keenable
#   scraperProvider: keenable
#   rerankerType: none          # Rerankers all require a key; 'none' skips reranking
#   # keenableApiKey: '${KEENABLE_API_KEY}'   # Optional: a key only lifts rate limits (public endpoints used when unset)
#   # keenableApiUrl: '${KEENABLE_API_URL}'   # Optional: search API URL override (fetch uses KEENABLE_FETCH_URL)
#   keenableSearchOptions:
#     maxResults: 5             # 1-20 results per search (default: 8)
#     # site: example.com       # Restrict search to a single domain
#     # attributionTitle: LibreChat  # X-Keenable-Title header sent with each request
#     # timeout: 15000          # HTTP request timeout in milliseconds (max 120000)
#   keenableScraperOptions:
#     # attributionTitle: LibreChat  # X-Keenable-Title header sent with each fetch
#     timeout: 15000            # HTTP request timeout in milliseconds (max 120000)
#
# Keenable search paired with another scraper (Firecrawl here) also works; each
# category is configured independently:
# webSearch:
#   searchProvider: keenable
#   scraperProvider: firecrawl
#   firecrawlApiKey: '${FIRECRAWL_API_KEY}'
#
# The reverse (someone else's search, Keenable as the scraper) also works. Pin
# the stack for every user as shown below, or leave the providers unpinned so
# each user can save this same keyless combination in the API-key dialog:
# webSearch:
#   searchProvider: searxng
#   searxngInstanceUrl: '${SEARXNG_INSTANCE_URL}'
#   scraperProvider: keenable
#   rerankerType: none
#
# SearXNG as the search provider example:
# webSearch:
#   searchProvider: searxng
#   searxngInstanceUrl: '${SEARXNG_INSTANCE_URL}'
#   # searxngApiKey: '${SEARXNG_API_KEY}'
#   searxngSearchOptions:
#     # Engines your instance should query. Accepts a comma-separated string or a list.
#     # Defaults to 'google,bing,duckduckgo'; DuckDuckGo serves CAPTCHAs to most
#     # self-hosted instances, so override it when results come back empty.
#     #
#     # Names must match engines enabled on your own instance. SearXNG ignores an
#     # engine it does not know instead of reporting an error, so a typo or a
#     # disabled engine shows up as fewer results rather than a failure. Check the
#     # enabled list at https://your-instance/config before setting this.
#     engines:
#       - google
#       - bing
#       - startpage
#       - qwant
#     # language: en            # Result language code (default: 'all')
#     # timeRange: month        # 'day', 'month', or 'year'
#     # timeout: 10000          # HTTP request timeout in milliseconds (1-120000, default: 10000)

# Memory configuration for user memories
# memory:
#   # (optional) Disable memory functionality
#   disabled: false
#   # (optional) Restrict memory keys to specific values to limit memory storage and improve consistency
#   validKeys: ["preferences", "work_info", "personal_info", "skills", "interests", "context"]
#   # (optional) Maximum token limit for stored memory values
#   tokenLimit: 10000
#   # (optional) Maximum tokens from recent chat sent to the memory agent before truncation
#   maxInputTokens: 12000
#   # (optional) Enable personalization features (defaults to true if memory is configured)
#   # When false, users will not see the Personalization tab in settings
#   personalize: true
#   # (optional) Memory agent configuration for automatic memory updates from chat messages.
#   # If omitted, users can still create, edit, delete, and reference memories manually.
#   agent:
#     # Explicitly enables automatic memory updates from chat messages.
#     enabled: true
#     # Option 1: Use existing agent by ID
#     id: "your-memory-agent-id"
#     # Option 2: Define agent inline
#     # provider: "openai"
#     # model: "gpt-4o-mini"
#     # instructions: "You are a memory management assistant. Store and manage user information accurately."
#     # model_parameters:
#     #   temperature: 0.1

# Apply opt-in content filters to source-classified submitted and reusable content.
# `filters` is base-config-only: database overrides and tombstones cannot add,
# change, or remove this policy for individual users, groups, or roles.
# In multi-replica deployments, use a coordinated deploy or restart and verify
# every replica loaded the same base config before considering policy active;
# local cache invalidation is not a rollout barrier.
# Omit `filters` or a source to leave that scope disabled. Omitting a source's
# `pii` block disables its source-aware detectors; for messages, `inspect` can
# still change how an enabled legacy `messageFilter.pii` attributes old rows.
# Omit `fields` to filter every supported field for an enabled source.
# `starterPatterns` and `customPatterns` can be configured independently
# under any source so each input surface can use a different policy. Starter
# ids are closed to the catalog below. Custom regexes use bounded,
# linear-time syntax; unsupported constructs are rejected at config load.
# `action` defaults to `block`. Set it to `audit` for a shadow rollout that
# records raw-free findings without rejecting or modifying content. Redaction
# is intentionally not an action yet because safe replacement requires a
# mutation-aware boundary and match spans; configuring an unsupported action
# is rejected rather than silently treated as enforcement.
# Omit `starterPatterns` to enable the full starter catalog; set it to `[]`
# to disable starters while retaining any configured custom patterns.
# Enabling or changing this policy does not rewrite or delete stored records.
# Current policy rechecks protected fields when they are resubmitted and when
# records are copied, shared, or become model-bound. Safe partial metadata edits
# can succeed so records remain repairable, but persisted protected fields remain
# unusable on those paths until repaired. Protected prompt or preset fields may
# be blanked with `contentFilterBlocked: true` in management views. Prompt-group
# metadata blocked by policy returns an explicit error on direct GET, while
# collection and reuse responses omit that group.
# Automatic memory maintenance may log and skip a rejected background update
# while allowing the main chat response to continue.
# Legacy assistant rows without provenance default to `model_output`, preserving
# legacy behavior. Inventory or migrate those records before relying on retroactive
# enforcement. Opting into `inspect` treats otherwise unattributed assistant content,
# including selected attachment projections, as submitted; explicit model provenance
# remains exempt.
# Roll out strict file inspection deliberately: `uninspectable: block` can make
# older opaque files unavailable for reuse until inspectable text is present.
# filters:
#   messages:
#     unattributedAssistantContent: model_output # `model_output` (default) or `inspect`
#     pii:
#       action: audit # `block` (default), `audit`, or opt-in `redact`
#       # `redact` transforms fresh, text-only interactive Agent chat submissions with a clientRequestId.
#       # Edits, resumes, files, quotes, other endpoints, and other fields still use blocking checks.
#       # Requires a valid CREDS_KEY. Preserve that key for owner-original recovery; changing it
#       # makes existing originals unavailable. Text remains canonical/filtered in ordinary exports.
#       # Originals are an encrypted, unindexed sidecar field, deleted/expired with the message.
#       # maxCharacters: 65536 # bounded total inspected text per transformation session
#       # maxMatches: 256 # bounded matches per transformation session
#       # Custom patterns may set category: email, phone, name, credential, or custom.
#       fields: [name, text, summary, quote, answer, decision_response, decision_reason, content_part, attachment_reference, assembled_context]
#       starterPatterns: [sk_prefix, bearer_header, api_key_header]
#       customPatterns:
#         - id: organization_identifier
#           label: Organization identifier
#           regex: "ORG-[A-Z0-9]{12}"
#   prompts:
#     pii:
#       fields: [name, description, oneliner, category, command, text, preset_text, system, context, instructions, additional_instructions, greeting, example_input, example_output]
#   agentInstructions:
#     pii:
#       fields: [name, category, description, instructions, additional_instructions, edge_description, edge_prompt, edge_prompt_key, artifacts, support_contact_name, support_contact_email]
#   conversationStarters:
#     pii:
#       fields: [text]
#   conversationTitles:
#     pii:
#       fields: [title]
#   feedback:
#     pii:
#       fields: [text]
#   skills:
#     pii:
#       fields: [name, display_title, description, category, frontmatter, instructions, imported_text, file_name, file_text]
#   memories:
#     pii:
#       fields: [key, value, summary]
#   files:
#     pii:
#       fields: [name, content, extracted_text, transcript, uri]
#       # `allow` is the compatibility default. `block` rejects opaque or
#       # oversized selected file content before provider/storage side effects.
#       uninspectable: block
#   toolArguments:
#     pii:
#       fields: [name, arguments, output]
#   modelParameters:
#     pii:
#       fields: [stop, request_fields, response_format, metadata]
#   actionMetadata:
#     pii:
#       fields: [raw_spec, domain, privacy_policy_url, authorization_type, custom_auth_header, authorization_content_type, authorization_url, client_url, scope, token_exchange_method, api_key, oauth_client_id, oauth_client_secret]

# Legacy message-only filter configuration. Existing deployments can continue
# using this shape while migrating message policy into `filters.messages`.
# When both shapes are configured, both policies apply. Prefer
# `filters.messages` for centrally managed source-aware policy.
# messageFilter:
#   pii:
#     # (optional) Pick a subset of the starter catalog by id; omit to
#     # enable all starters (sk_prefix, bearer_header, api_key_header).
#     starterPatterns: [sk_prefix, bearer_header, api_key_header]
#     # (optional) Operator-defined patterns. Each entry needs id, label,
#     # and a regex in RE2 syntax and semantics (RE2 is a linear-time engine
#     # with no catastrophic backtracking; a few escapes such as \p, \A, and
#     # \s differ from JavaScript). Backreferences and lookaround are not
#     # supported; the regex is validated against the RE2 engine at config
#     # load time and a pattern it cannot compile is rejected.
#     customPatterns:
#       - id: anthropic_api_key
#         label: Anthropic API key
#         regex: "sk-ant-[A-Za-z0-9_-]{20,}"

# ACL writes retry only conflicts on an individual document.
# permissions:
#   maxWriteAttempts: 3 # Integer 1-100, including the first attempt.
#   leaseTtlMs: 30000 # Integer 1000-600000. Sharing updates on deployments without transactions hold a per-resource lease this long between renewals.
#   leaseWaitMs: 3000 # Integer 0-60000. How long an update waits for a contended lease before answering 409.