Jump to content

Connect SuperML | Leeroopedia MCP: Equip your AI agents with best practices, code verification, and debugging knowledge. Powered by Leeroo — building Organizational Superintelligence. Contact us at founders@leeroo.com.

Implementation:Langchain ai Langgraph CLI Config Schema V0

From Leeroopedia
Revision as of 11:25, 16 February 2026 by Admin (talk | contribs) (Auto-imported from implementations/Langchain_ai_Langgraph_CLI_Config_Schema_V0.md)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Knowledge Sources
Domains CLI, Configuration
Last Updated 2026-02-11 16:00 GMT

Overview

The V0 configuration schema (`schema.v0.json`) is the legacy version of the JSON Schema for the `langgraph.json` configuration file, providing the same structural specification as the current schema with minor differences in supported image distributions for Node.js deployments.

Description

This JSON Schema file (`schema.v0.json`) represents the original version (v0) of the LangGraph CLI configuration specification. It is structurally identical to the current `schema.json` in most respects, defining the same top-level `Config` with `oneOf` discriminating between Python and Node.js deployment modes, and the same set of sub-configurations for authentication, HTTP, checkpointing, store, webhooks, encryption, and Docker image settings.

The V0 schema shares the same comprehensive configuration hierarchy: `AuthConfig` for custom authentication with OpenAPI integration, `HttpConfig` for server route control and CORS, `CheckpointerConfig` for TTL-based state cleanup and serialization, `StoreConfig` for long-term memory with optional vector indexing, and `WebhooksConfig` for outbound event delivery with URL policies. All field definitions, types, and descriptions are identical between the two schema versions.

The primary distinction between the V0 schema and the current schema is subtle. Both schemas include the same set of features (auth, HTTP, store, checkpointer, webhooks, encryption, UI, etc.) and both support Python and Node.js deployment configurations. The V0 schema is retained for backward compatibility with existing deployments that reference this specific schema version, ensuring that older `langgraph.json` files continue to validate correctly.

Usage

Use this schema version when working with legacy LangGraph deployments that were configured against the V0 specification. New deployments should use the current `schema.json` instead. The CLI tooling may reference this schema when processing older configuration files for backward compatibility.

Code Reference

Source Location

Signature

{
  "$ref": "#/$defs/Config",
  "title": "LangGraph CLI Configuration",
  "description": "Configuration schema for langgraph-cli",
  "version": "v0",
  "$defs": {
    "Config": { "oneOf": [ /* Python config */, /* Node.js config */ ] },
    "AuthConfig": { /* path, openapi, cache, disable_studio_auth */ },
    "HttpConfig": { /* app, cors, disable_*, configurable_headers, ... */ },
    "CheckpointerConfig": { /* ttl, serde, sweep_limit */ },
    "StoreConfig": { /* index, ttl */ },
    "IndexConfig": { /* embed, dims, fields */ },
    "WebhooksConfig": { /* url, headers, env_prefix */ },
    "CorsConfig": { /* allow_origins, allow_methods, allow_headers, ... */ },
    "EncryptionConfig": { /* path */ },
    ...
  }
}

Import

# Referenced by the CLI tooling for backward compatibility; not imported as Python code.
# Located at: libs/cli/schemas/schema.v0.json

I/O Contract

Top-Level Config (Python Deployment)
Field Type Required Description
`dependencies` `array[string]` Yes Python dependencies to install from PyPI or local paths
`graphs` `object` Yes Named graph definitions pointing to Python objects
`python_version` `string` No Python version (`3.11`, `3.12`, `3.13`)
`env` string` No Environment variables as dict or path to `.env` file
`auth` null` No Custom authentication configuration
`http` null` No HTTP server configuration
`store` null` No Long-term memory store configuration
`checkpointer` null` No State checkpointing configuration
`webhooks` null` No Outbound webhook event delivery
`encryption` null` No At-rest encryption configuration
`base_image` null` No Base Docker image
`image_distro` debian | wolfi | null` No Linux distribution for base image
`dockerfile_lines` `array[string]` No Additional Docker instructions
`pip_installer` null` No Package installer (`auto`, `pip`, `uv`)
`ui` null` No UI component definitions
`api_version` null` No LangGraph API server version
Top-Level Config (Node.js Deployment)
Field Type Required Description
`node_version` null` Yes Node.js major version
`graphs` `object` Yes Named graph definitions
`dependencies` `array[string]` No Dependencies to install
`image_distro` wolfi | null` No Linux distribution for base image
Schema Definitions
Definition Key Fields Description
`AuthConfig` `path`, `openapi`, `cache`, `disable_studio_auth` Custom authentication with OpenAPI security
`HttpConfig` `app`, `cors`, `disable_*`, `configurable_headers` HTTP server and route configuration
`StoreConfig` `index`, `ttl` Long-term memory with optional vector search
`CheckpointerConfig` `ttl`, `serde`, `sweep_limit` State checkpointing and TTL cleanup
`WebhooksConfig` `url`, `headers`, `env_prefix` Outbound webhook event delivery
`EncryptionConfig` `path` Custom at-rest encryption

Usage Examples

{
  "dependencies": ["langchain-openai", "./my_agent"],
  "graphs": {
    "my_graph": "my_agent.graph:compiled_graph"
  },
  "python_version": "3.11",
  "env": {
    "OPENAI_API_KEY": "sk-..."
  },
  "store": {
    "index": {
      "embed": "openai:text-embedding-3-small",
      "dims": 1536
    },
    "ttl": {
      "default_ttl": 1440,
      "refresh_on_read": true,
      "sweep_interval_minutes": 10
    }
  },
  "checkpointer": {
    "ttl": {
      "strategy": "delete",
      "default_ttl": 120
    }
  }
}

Related Pages

Page Connections

Double-click a node to navigate. Hold to expand connections.
Principle
Implementation
Heuristic
Environment