# Algo/AI

## Integration Approach

* User creates a vault via rethink.finance
* User grants their script specific permissions
* User script executes trades through the vaults [Roles Modifier](https://docs.rethink.finance/rethink.finance/protocol/architecture#zodiac-roles-modifier) contract

## Technical Implementation:

* Route all transaction calls through the vault's Roles Modifier
* All transaction execution will use the `execTransactionWithRole` function on the role modifier contract
  * ABI: <https://raw.githubusercontent.com/rethink-finance/rethink-frontend/refs/heads/main/src/contracts/zodiac/RolesFull.json>
  * `execTransactionWithRole` def: <https://github.com/gnosisguild/zodiac-modifier-roles-v1/blob/main/packages/evm/contracts/Roles.sol#L364-L378>
* Your bot will only have permission to execute specific trading functions with predefined parameter limits

## Data Storage and Configuration

* Store vault contract address and role ID directly in the users AWS instance (env or parameter store, or in script directly)

## Psuecode of Intergration

```python
# 1. Build the transaction data using SDK
w3 = Web3()
sdk = GainsTradingSDK()
tx_data = sdk.build.openTrade(trade_params_here)

# 2. Create role modifier contract instance
role_modifier = w3.eth.contract(
    address=QIV_ROLE_MODIFIER,  # Obtained during the user onboarding process
    abi=ROLE_MODIFIER_ABI  # We just have this file
)

# 3. Execute through vault's role modifier
tx = role_modifier.functions.execTransactionWithRole(
    tx_data.to,  # G-Trade address
    0,  # No ETH value
    tx_data.data,  # Trading function data
    0,  # Call (not delegatecall)
    ROLE_ID,  # Obtained during the user onboarding process
    True
).build_transaction({
    'from': "some_address",
    'gas': 2000000,
    'nonce': "some_nonce"
})

# 4. Sign
signed_tx = w3.eth.account.sign_transaction(tx, "some_private_key")
tx_hash = w3.eth.send_raw_transaction(signed_tx.rawTransaction)

```