> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agentchain.cloud/llms.txt
> Use this file to discover all available pages before exploring further.

# Policies

> On-chain rules that constrain what agents are allowed to do.

Policies define the **permission boundary** for an agent. Before an agent's action can be verified as compliant, it must have a registered policy on-chain that explicitly allows the targets and selectors it used.

***

## What Is a Policy?

A policy is an on-chain record in the `AgentPolicy` contract that defines:

| Field              | Type        | Purpose                                              |
| ------------------ | ----------- | ---------------------------------------------------- |
| `agentId`          | `address`   | The agent wallet this policy applies to              |
| `rulesetHash`      | `bytes32`   | Hash of the full ruleset document (stored off-chain) |
| `allowedTargets`   | `address[]` | Contract addresses the agent is allowed to call      |
| `allowedSelectors` | `bytes4[]`  | Function selectors the agent is allowed to invoke    |

<Info>
  **Policies are additive.** An agent can register multiple policies. The ActionVerifier checks if the action's target and selector appear in **any** of the agent's active policies.
</Info>

***

## Registering a Policy

Call `AgentPolicy.registerPolicy()` with the agent's allowed targets and selectors:

<CodeGroup>
  ```bash cast (Foundry) theme={null}
  # Allow agent to call Uniswap V3 Router's exactInputSingle
  cast send 0xbccb85e016350d3439c794a7903e3fd224c1be3c \
    "registerPolicy(address,bytes32,address[],bytes4[])" \
    YOUR_AGENT_ADDRESS \
    $(cast keccak "uniswap-v3-swap-only") \
    "[0x2626664c2603336E57B271c5C0b26F421741e481]" \
    "[0x414bf389]" \
    --rpc-url https://sepolia.base.org \
    --private-key YOUR_AGENT_PRIVATE_KEY
  ```

  ```typescript viem theme={null}
  import { createWalletClient, http, encodeFunctionData } from 'viem';
  import { baseSepolia } from 'viem/chains';

  const tx = await walletClient.writeContract({
    address: '0xbccb85e016350d3439c794a7903e3fd224c1be3c',
    abi: agentPolicyAbi,
    functionName: 'registerPolicy',
    args: [
      agentAddress,
      keccak256(toHex('uniswap-v3-swap-only')),
      ['0x2626664c2603336E57B271c5C0b26F421741e481'], // Uniswap V3 Router
      ['0x414bf389'],                                   // exactInputSingle selector
    ],
  });
  ```
</CodeGroup>

***

## Policies Enable Fast-Path Settlement

The policy registry is deeply integrated with the protocol's dispute resolution mechanism. If an action's verified outcome (`stateMatch`) is contested on-chain, the `BisectionCourtV3` uses the agent's policy in its deterministic fast-path:

Because the `ActionVerifier` is a deterministic state transition evaluator, disputes over EVM actions do not require the traditional 10-round interactive bisection game. The court simply pulls the agent's policy, executes a single-step verify, and settles the 1 ETH dispute instantly. Policies make this trustless automation possible.

***

## How Policies Are Enforced

When `ActionVerifier.verifyAction()` runs, it checks each transaction in the action payload:

```
For each transaction:
  1. Is transaction.target in agentPolicy.allowedTargets[agentId]?
     → No: violationCode = 1 (UNAUTHORIZED_TARGET)
  2. Is transaction.selector in agentPolicy.allowedSelectors[agentId]?
     → No: violationCode = 2 (UNAUTHORIZED_SELECTOR)
  3. Both pass: policyCompliant = true
```

### Violation Codes

| Code | Name                    | Meaning                                                       |
| ---- | ----------------------- | ------------------------------------------------------------- |
| 0    | `NONE`                  | No violation — action is policy-compliant                     |
| 1    | `UNAUTHORIZED_TARGET`   | The contract address is not in the agent's allowed targets    |
| 2    | `UNAUTHORIZED_SELECTOR` | The function selector is not in the agent's allowed selectors |

***

## Policy Design Patterns

### Minimal Permission (Recommended)

Register the exact targets and selectors your agent needs. Nothing more.

```
Allowed targets:   [UniswapRouter, WETH, USDC]
Allowed selectors: [exactInputSingle, approve, transfer]
```

### Broad Permission (Development Only)

For testing, you can register a wildcard policy. **Do not use in production.**

```
Allowed targets:   [0x0000...0000]  // special: matches all targets
Allowed selectors: [0x00000000]     // special: matches all selectors
```

<Warning>
  **Wildcard policies bypass all compliance checks.** The ActionVerifier will always return `policyCompliant: true` regardless of what the agent does. This is dangerous and should only be used on testnets.
</Warning>

***

## Contract Details

| Property    | Value                                        |
| ----------- | -------------------------------------------- |
| Contract    | AgentPolicy (UUPS proxy)                     |
| Address     | `0xbccb85e016350d3439c794a7903e3fd224c1be3c` |
| Network     | Base Sepolia (84532)                         |
| Owner       | AgentChainHelm V2 (`0x4f98...485e`)          |
| Upgradeable | Yes — via Helm executeUpgrade (48h timelock) |