Struct AgentRuntimePolicy 

pub struct AgentRuntimePolicy {
    pub max_steps: usize,
    pub output_retries: usize,
    pub end_strategy: AgentEndStrategy,
    pub tool_execution: AgentToolExecutionMode,
}

Runtime policy for bare agent runs.

Fields

max_steps: usize

Maximum model requests in one run.

output_retries: usize

Maximum output validation retries.

end_strategy: AgentEndStrategy

How to handle ordinary tool calls returned alongside a final output function.

tool_execution: AgentToolExecutionMode

How to schedule batches of model-returned tool calls.

Trait Implementations

impl Clone for AgentRuntimePolicy

fn clone(&self) -> AgentRuntimePolicy

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for AgentRuntimePolicy

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

Formats the value using the given formatter.

impl Default for AgentRuntimePolicy

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for AgentRuntimePolicy

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Eq for AgentRuntimePolicy

impl PartialEq for AgentRuntimePolicy

fn eq(&self, other: &AgentRuntimePolicy) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for AgentRuntimePolicy

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for AgentRuntimePolicy