Struct PacingConfig 

pub struct PacingConfig {
    pub step_timeout_secs: Option<u64>,
    pub loop_detection_min_elapsed_secs: Option<u64>,
    pub loop_ignore_tools: Vec<String>,
    pub message_timeout_scale_max: Option<u64>,
    pub loop_detection_enabled: bool,
    pub loop_detection_window_size: usize,
    pub loop_detection_max_repeats: usize,
}

Pacing controls for slow/local LLM workloads ([pacing] section).

All fields are optional and default to values that preserve existing behavior. When set, they extend — not replace — the existing timeout and loop-detection subsystems.

Fields

step_timeout_secs: Option<u64>

Per-step timeout in seconds: the maximum time allowed for a single LLM inference turn, independent of the total message budget. None means no per-step timeout (existing behavior).

loop_detection_min_elapsed_secs: Option<u64>

Minimum elapsed seconds before loop detection activates. Tasks completing under this threshold get aggressive loop protection; longer-running tasks receive a grace period before the detector starts counting. None means loop detection is always active (existing behavior).

loop_ignore_tools: Vec<String>

Tool names excluded from identical-output / alternating-pattern loop detection. Useful for browser workflows where browser_screenshot structurally resembles a loop even when making progress.

message_timeout_scale_max: Option<u64>

Override for the hardcoded timeout scaling cap (default: 4). The channel message timeout budget is computed as: message_timeout_secs * min(max_tool_iterations, message_timeout_scale_max) Raising this value lets long multi-step tasks with slow local models receive a proportionally larger budget without inflating the base timeout.

loop_detection_enabled: bool

Enable pattern-based loop detection (exact repeat, ping-pong, no-progress). Defaults to true.

loop_detection_window_size: usize

Sliding window size for the pattern-based loop detector. Defaults to 20.

loop_detection_max_repeats: usize

Number of consecutive identical tool+args calls before the first escalation (Warning). Defaults to 3.

Trait Implementations

impl Clone for PacingConfig

fn clone(&self) -> PacingConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for PacingConfig

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

Formats the value using the given formatter.

impl Default for PacingConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for PacingConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl JsonSchema for PacingConfig

fn schema_name() -> Cow<'static, str>

The name of the generated JSON Schema.

fn schema_id() -> Cow<'static, str>

Returns a string that uniquely identifies the schema produced by this type.

fn json_schema(generator: &mut SchemaGenerator) -> Schema

Generates a JSON Schema for this type.

fn inline_schema() -> bool

Whether JSON Schemas generated for this type should be included directly in parent schemas, rather than being re-used where possible using the $ref keyword.

impl Serialize for PacingConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.