Struct LimitsSection 

pub struct LimitsSection {
    pub max_search_rounds: Option<usize>,
    pub subagent_max_depth: Option<usize>,
    pub max_concurrent_runs: Option<usize>,
    pub goal_eval_transcript_tail: Option<usize>,
}

[limits] section. Various runtime limits and thresholds.

Falls back to individual RECURSIVE_* env vars.

Example:

[limits]
max_search_rounds = 5
subagent_max_depth = 3
max_concurrent_runs = 8
goal_eval_transcript_tail = 12

Fields

max_search_rounds: Option<usize>

Maximum number of ToolSearchTool round-trips per complete_with_search / stream_with_search call. Corresponding env var: RECURSIVE_MAX_SEARCH_ROUNDS. Default: 3.

subagent_max_depth: Option<usize>

Maximum nesting depth for sub-agents and parallel workers. Corresponding env var: RECURSIVE_SUBAGENT_MAX_DEPTH. Default: 2.

max_concurrent_runs: Option<usize>

Maximum number of concurrent agent runs across all HTTP endpoints. Corresponding env var: RECURSIVE_MAX_CONCURRENT_RUNS. Default: 8.

goal_eval_transcript_tail: Option<usize>

Number of most-recent transcript messages passed to the goal evaluator judge on each turn. Corresponding env var: RECURSIVE_GOAL_EVAL_TRANSCRIPT_TAIL. Default: 12.

Trait Implementations

impl Clone for LimitsSection

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 LimitsSection

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

Formats the value using the given formatter.

impl Default for LimitsSection

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for LimitsSection

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.