Skip to content

en deploy settings

langbot-wiki-sync[bot] edited this page Jul 29, 2026 · 3 revisions

System Environment Settings

Configure system runtime settings in data/config.yaml. Generally, no modification is needed.

admins: []
api:
    port: 5300
    webhook_prefix: 'http://127.0.0.1:5300'
    extra_webhook_prefix: ''
    global_api_key: ''  # Global API key. When non-empty, it is accepted for both the HTTP API and the MCP server (/mcp) with no login session, no database record, and no lbk_ prefix required. Empty = disabled. Stored in plaintext — enable only on trusted/internal deployments and serve over HTTPS.
command:
    enable: true
    prefix:
    - '!'
    - 
    privilege: {}
concurrency:
    pipeline: 20
    session: 1
proxy:
    http: ''
    https: ''
system:
    instance_id: ''
    edition: community
    recovery_key: ''
    allow_modify_login_info: true
    disabled_adapters: []
    limitation:
        max_bots: -1
        max_pipelines: -1
        max_extensions: -1
    task_retention:
        # Keep at most this many completed async task records in memory
        completed_limit: 200
    jwt:
        expire: 604800
        secret: ''
database:
    use: sqlite
    sqlite:
        path: 'data/langbot.db'
    postgresql:
        host: '127.0.0.1'
        port: 5432
        user: 'postgres'
        password: 'postgres'
        database: 'postgres'
vdb:
    use: chroma
    qdrant:
        url: ''
        host: localhost
        port: 6333
        api_key: ''
    seekdb:
        mode: embedded  # 'embedded' or 'server'
        # Embedded mode options:
        path: './data/seekdb'
        database: 'langbot'
        # Server mode options (used when mode='server'):
        host: 'localhost'
        port: 2881
        user: 'root'
        password: ''
        tenant: ''  # Optional, for OceanBase server
    milvus:
        uri: 'http://127.0.0.1:19530'
        token: ''
        db_name: ''
    pgvector:
        host: '127.0.0.1'
        port: 5433
        database: 'langbot'
        user: 'postgres'
        password: 'postgres'
    valkey_search:
        host: 'localhost'
        port: 6379
        db: 0
        username: ''      # Optional (ACL user)
        password: ''      # Optional (ACL / requirepass), never logged
        tls: false        # Optional, for toB/SaaS deployments
        index_algorithm: 'HNSW'    # HNSW (approximate) or FLAT (exact)
        distance_metric: 'COSINE'  # COSINE, L2, or IP
        request_timeout: 5000      # Per-request timeout in ms
storage:
    use: local
    cleanup:
        # Enable periodic cleanup of local/S3 uploaded files and old log files
        enabled: true
        # Cleanup check interval in hours
        check_interval_hours: 1
        # Root-level uploaded files older than this will be deleted
        uploaded_file_retention_days: 7
        # LangBot log files older than this many days will be deleted
        log_retention_days: 3
    s3:
        endpoint_url: ''
        access_key_id: ''
        secret_access_key: ''
        region: 'us-east-1'
        bucket: 'langbot-storage'
plugin:
    enable: true
    runtime_ws_url: 'ws://langbot_plugin_runtime:5400/control/ws'
    enable_marketplace: true
    display_plugin_debug_url: 'ws://localhost:5401/plugin/debug/ws'
    binary_storage:
        # Max bytes for a single plugin binary storage value
        max_value_bytes: 10485760
monitoring:
    auto_cleanup:
        # Enable automatic cleanup of expired monitoring records
        enabled: true
        # Retention period in days, records older than this will be deleted
        retention_days: 30
        # Cleanup check interval in hours
        check_interval_hours: 1
        # Number of expired rows to delete per table batch
        delete_batch_size: 1000
box:
    enabled: true  # Master switch for Box Runtime. When false, Box-dependent features such as sandbox tools, Skill add/edit, and stdio MCP are disabled.
    backend: 'local'  # 'local' (Docker/nsjail), 'docker', 'nsjail', or 'e2b'. Can be written via BOX__BACKEND.
    runtime:
        endpoint: ''  # External Box Runtime base URL, e.g. 'ws://127.0.0.1:5410'. When empty, non-Docker deployments use a locally managed Runtime; Docker deployments connect to langbot_box:5410 on the Compose network.
    local:
        profile: 'default'
        image: ''  # Custom local sandbox image. Leave empty to use the profile default.
        host_root: './data/box'  # Base host directory for local workspace mounts. Docker deployments should use an absolute host path mounted by langbot_box.
        default_workspace: ''  # Defaults to '<host_root>/default'.
        skills_root: 'skills'  # Box-owned Skill package directory. Relative paths are resolved under host_root.
        allowed_mount_roots:  # Defaults to ['<host_root>'] when left empty.
            - './data/box'
            - '/tmp'
        workspace_quota_mb: null  # Optional disk quota override (>= 0). null = profile default.
    default_memory_mb: 1536  # Default nsjail cgroup memory limit per MCP stdio process (MB). Node.js MCP servers (npx/bunx) need more than Python ones due to V8 + WASM overhead. Too low = return_code=137 (OOM). Override per-server with box.memory_mb. Env: BOX__DEFAULT_MEMORY_MB.
    docker:
        cpu_limit_enabled: true  # When false, Docker sandbox containers are started without --cpus. Memory and PID limits still apply.
    e2b:
        api_key: ''  # Can also be set via E2B_API_KEY env var.
        api_url: ''  # Custom API URL for self-hosted deployments.
        template: ''  # Default template ID (e.g. 'base', 'python-3.11').
space:
    # Space service URL for OAuth and API
    url: 'https://space.langbot.app'
    # Space API URL for model requests (MaaS)
    models_gateway_api_url: 'https://api.langbot.cloud/v1'
    # OAuth authorization page URL
    oauth_authorize_url: 'https://space.langbot.app/auth/authorize'
    disable_models_service: false
    disable_telemetry: false

Notes

  • storage.cleanup.uploaded_file_retention_days only cleans temporary uploaded files at the storage root. It does not delete plugin configuration files or internal objects stored under directories.
  • storage.cleanup.log_retention_days cleans old log files by the date in their file names. The default keeps at most 3 days of logs.
  • When SQLite is used as the database, automatic monitoring cleanup directly releases database file space after deleting expired records.
  • plugin.binary_storage.max_value_bytes limits the size of a single plugin binary storage value. The default is 10 MiB.
  • The WebUI sidebar includes a “Storage Analysis” page for viewing database, logs, uploaded files, vector store, plugins, MCP, temporary files, and cleanup candidates.
  • vdb.valkey_search uses the Valkey Search module via the official async valkey-glide client and supports vector, full-text, and hybrid search. Run a server with the module loaded, e.g. valkey/valkey-bundle:9.1.0 (docker run -d -p 6379:6379 valkey/valkey-bundle:9.1.0). Note: hybrid search follows a filter-then-KNN model, so the vector_weight parameter is accepted but not honored (a native Valkey Search limitation). The connection is lazy, so a down or misconfigured server does not block startup. See the Valkey Search integration doc for details.
  • api.global_api_key is a global API key for agents / automation: once set, calls to the HTTP API or the built-in MCP server (/mcp) authenticate by sending X-API-Key: <key> or Authorization: Bearer *** — no login session and no database-stored lbk_key required. It is stored in plaintext inconfig.yaml`, so enable it only on trusted / internal deployments and serve it over HTTPS. See API Key Authentication.

Set Configuration Via Environment Variables

The configuration in config.yaml can be set via environment variables. Environment variable names use uppercase letters and double underscores, for example: API__PORT represents api.port.

  • API__PORT represents api.port
  • CONCURRENCY__PIPELINE represents concurrency.pipeline
  • DATABASE__SQLITE__PATH represents database.sqlite.path
  • STORAGE__CLEANUP__UPLOADED_FILE_RETENTION_DAYS represents storage.cleanup.uploaded_file_retention_days
  • STORAGE__CLEANUP__LOG_RETENTION_DAYS represents storage.cleanup.log_retention_days
  • MONITORING__AUTO_CLEANUP__RETENTION_DAYS represents monitoring.auto_cleanup.retention_days
  • PLUGIN__BINARY_STORAGE__MAX_VALUE_BYTES represents plugin.binary_storage.max_value_bytes
  • BOX__BACKEND represents box.backend
  • BOX__LOCAL__HOST_ROOT represents box.local.host_root
  • BOX__LOCAL__SKILLS_ROOT represents box.local.skills_root

On startup, LangBot reads all environment variables, applies the corresponding configuration to config.yaml, and writes it to data/config.yaml.

Note

Set Box-related configuration on the langbot service with the unified BOX__* environment variables. LangBot applies them to data/config.yaml on startup and sends the Box configuration to langbot_box through INIT RPC. Do not set LANGBOT_BOX_* or BOX__* on the langbot_box service; they are not read directly there.

LangBot Documentation

Home

简体中文
指南
开发者
API 参考
Other pages
English
Guides
Developers
API Reference
Other pages
日本語
ガイド
開発者
API リファレンス
Other pages

Clone this wiki locally