Struct MontyOneShotExecutor 

pub struct MontyOneShotExecutor { /* private fields */ }

Available on crate feature code only.

One-shot Monty executor: a fresh interpreter per execute call.

Build with MontyExecutorBuilder::build_one_shot. Lifecycle methods keep the no-op trait defaults — every call is independent. See the module docs for the security model.

Example

use adk_code::{
    CodeExecutor, ExecutionLanguage, ExecutionPayload, ExecutionRequest,
    MontyExecutorBuilder, SandboxPolicy,
};

let executor = MontyExecutorBuilder::new().build_one_shot()?;
let request = ExecutionRequest {
    language: ExecutionLanguage::Python,
    payload: ExecutionPayload::Source { code: "1 + 1".to_string() },
    argv: vec![],
    stdin: None,
    input: None,
    sandbox: SandboxPolicy::strict_python(),
    identity: None,
};
let result = executor.execute(request).await?;
assert_eq!(result.output, Some(serde_json::json!(2)));

Implementations

impl MontyOneShotExecutor

pub fn granted_policy(&self) -> SandboxPolicy

Available on crate feature embedded-python only.

A SandboxPolicy requesting exactly this executor’s grants.

The per-request policy may only narrow within the grants, so SandboxPolicy::strict_python (no filesystem, no environment) runs fully sandboxed even on a granting executor. Use this policy to run with everything the executor offers.

Trait Implementations

impl CodeExecutor for MontyOneShotExecutor

fn name(&self) -> &str

Human-readable backend name.

fn capabilities(&self) -> BackendCapabilities

The capabilities this backend can enforce.

fn supports_language(&self, lang: &ExecutionLanguage) -> bool

Whether this backend supports the given language.

fn prompt_snippet(&self) -> Option<String>

A prose snippet describing this backend’s execution environment and built-in capabilities, suitable for appending to an LLM-facing tool description.

fn execute<'life0, 'async_trait>( &'life0 self, request: ExecutionRequest, ) -> Pin<Box<dyn Future<Output = Result<ExecutionResult, ExecutionError>> + Send + 'async_trait>>

where 'life0: 'async_trait, MontyOneShotExecutor: 'async_trait,

Execute a request and return a structured result.

fn start<'life0, 'async_trait>( &'life0 self, ) -> Pin<Box<dyn Future<Output = Result<(), ExecutionError>> + Send + 'async_trait>>

where 'life0: 'async_trait, Self: 'async_trait,

Start the execution environment (e.g., create and start a container).

fn stop<'life0, 'async_trait>( &'life0 self, ) -> Pin<Box<dyn Future<Output = Result<(), ExecutionError>> + Send + 'async_trait>>

where 'life0: 'async_trait, Self: 'async_trait,

Stop the execution environment and release resources.

fn restart<'life0, 'async_trait>( &'life0 self, ) -> Pin<Box<dyn Future<Output = Result<(), ExecutionError>> + Send + 'async_trait>>

where 'life0: 'async_trait, Self: 'async_trait,

Restart the execution environment.

fn is_running<'life0, 'async_trait>( &'life0 self, ) -> Pin<Box<dyn Future<Output = bool> + Send + 'async_trait>>

where 'life0: 'async_trait, Self: 'async_trait,

Whether the execution environment is currently running.

impl Debug for MontyOneShotExecutor

fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), Error>

Formats the value using the given formatter.