docs: fix HITL interrupt schema typos (args and camelCase for JS)

[Ezzat Esam (EzzatEsam)]

Overview

This PR corrects significant discrepancies in the Human-in-the-Loop (HITL) documentation for both Python and JavaScript.

1. Both: Corrects the key arguments to args within the tool request objects.
2. JavaScript/TypeScript: Fixes the casing and structure of the __interrupt__ object. The documentation incorrectly used snake_case (Python-style). The actual SDK output uses camelCase.

Type of change

Type: Fix typo

Related issues/PRs

N/A

Checklist

• I have read the contributing guidelines
• I have tested my changes locally using docs dev
• All code examples have been tested and work correctly
• I have used root relative paths for internal links
• I have updated navigation in src/docs.json if needed

Additional notes

The documentation was updated to reflect the actual runtime output of the __interrupt__ state.

Key Changes:

• Python: Updated arguments → args.
• JavaScript: * Updated arguments → args.
• Corrected property casing: action_requests → actionRequests, review_configs → reviewConfigs, action_name → actionName, and allowed_decisions → allowedDecisions.

I verified these changes by running the replication scripts provided below.

Python Replication Code

from langchain.agents import create_agent
from langchain.agents.middleware import HumanInTheLoopMiddleware
from langchain_core.tools import tool
from langgraph.checkpoint.memory import InMemorySaver
from langchain_google_genai import ChatGoogleGenerativeAI

@tool
def write_file(file_name: str, content: str) :
    """Write content to a file with the given file name and return the file path."""
    pass

agent = create_agent(
    model=ChatGoogleGenerativeAI(model="gemini-3-flash-preview", temperature=1),
    tools=[write_file],
    middleware=[
        HumanInTheLoopMiddleware(
            interrupt_on={"write_file": True},
            description_prefix="Tool execution pending approval",
        ),
    ],
    checkpointer=InMemorySaver(),
)

config = {"configurable": {"thread_id": "some_id"}}
result = agent.invoke(
    {"messages": [{"role": "user", "content": "Create a file named 'test.txt' with the content 'Hello, World!'"}]},
    config=config 
)

# Output confirmed to use 'args'
print(result['__interrupt__'])

JavaScript/TypeScript Replication Code

import "dotenv/config";
import { createAgent, humanInTheLoopMiddleware, HumanMessage } from "langchain";
import { MemorySaver } from "@langchain/langgraph";
import * as z from "zod";
import { tool } from "langchain";
import { ChatGoogleGenerativeAI } from "@langchain/google-genai";

const writeFileTool = tool(({ fileName, content }) => {}, {
  name: "write_file",
  description: "Write content to a file.",
  schema: z.object({
    fileName: z.string().describe("Name of the file to write to"),
    content: z.string().describe("Content to write into the file"),
  }),
});

const agent = createAgent({
  model: new ChatGoogleGenerativeAI("gemini-3-flash-preview"),
  tools: [writeFileTool],
  middleware: [
    humanInTheLoopMiddleware({
      interruptOn: { write_file: true },
      descriptionPrefix: "Tool execution pending approval",
    }),
  ],
  checkpointer: new MemorySaver(),
});

const config = { configurable: { thread_id: "some_id" } };

const result = await agent.invoke(
  {
    messages: [new HumanMessage("Create a file named 'test.txt' with the content 'Hello, World!'")],
  },
  config,
);

// Output confirmed to use camelCase (actionRequests, etc.) and 'args'
console.log(JSON.stringify(result.__interrupt__, null, 2));