Struct SystemPromptReport 

pub struct SystemPromptReport {
    pub token_estimate: u64,
    pub over_budget: bool,
    pub trimmed_sections: Vec<&'static str>,
}

Result of measuring a composed system prompt against the configured token budget (agent.max_system_prompt_tokens).

Fields

token_estimate: u64

estimate_token_count of the final composed text (after trimming, if trimming occurred).

over_budget: bool

Whether token_estimate exceeds agent.max_system_prompt_tokens.

trimmed_sections: Vec<&'static str>

Names of sections dropped to satisfy the budget, in drop order. Empty unless agent.trim_system_prompt is enabled and trimming occurred.

Implementations

impl SystemPromptReport

pub fn measure(text: &str, max_tokens: u64) -> Self

Measure text against max_tokens with no trimming applied.

Useful when a system prompt was assembled or overridden outside the normal section-based pipeline (e.g. downstream embedders calling AgentRunner::set_system_prompt, or appendix text appended after crate::prompts::system::compose_system_instruction_with_report already measured the sectioned prompt).

Trait Implementations

impl Clone for SystemPromptReport

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for SystemPromptReport

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

Formats the value using the given formatter.

impl Default for SystemPromptReport

fn default() -> Self

Returns the “default value” for a type.

impl PartialEq for SystemPromptReport

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

Equality operator ==.

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

Inequality operator !=.

impl StructuralPartialEq for SystemPromptReport