Arcezia / Integrations / LangChain and LangGraph

LangChain and LangGraph: check each tool call before it runs

Wrap your LangChain or LangGraph tools with Arcezia and each call is checked before it runs. Only ALLOW reaches the tool.

Setup

Before this: install the SDK, get a key and register a contract for your tool, as in Quickstart steps 1 to 5. SQL below is the contract domain from that Quickstart, and private_key is your signing key. Make one client and open the session:

from arcezia import Arcezia

az = Arcezia(task="look up orders", on_error="review", signing_key=private_key)
az.start_session(capability_envelope={
    "allowed_domains": [SQL],
    "allowed_action_types": ["execute_sql"],
    "resource_scope": ["orders"],
})

Wrap the tools

from arcezia.integrations.langchain import ArceziaToolkit

safe = ArceziaToolkit(az).wrap([execute_sql], domain_overrides={"execute_sql": SQL})
safe[0].run({"query": "SELECT COUNT(*) FROM orders"})   # raises ToolException on REVIEW or BLOCK

graph_tools = ArceziaToolkit(az).wrap_for_langgraph([execute_sql],
                                                    domain_overrides={"execute_sql": SQL})

wrap_for_langgraph returns real LangChain tools with the original argument schema, so they plug into LangGraph’s ToolNode and create_react_agent.

What you get

• ALLOW: the tool runs.
• REVIEW: the tool does not run; the exception names what would release it.
• BLOCK: the tool does not run; the exception gives the reason.

On a new key a call usually comes back REVIEW first. The answer names what would release it, for example a contract for the tool or a signed scope for the session. See Handling the answers.

Same answers everywhere. Every hookup calls the same service with the same rules. Switching frameworks does not change a verdict.