Struct StageSetup 

pub struct StageSetup {
    pub inference_config: InferenceConfig,
    pub routing: Option<ToolResultRouting>,
    pub accepts_messages: bool,
    pub context_layout: Option<ContextLayout>,
    pub system_prompt: Option<String>,
    pub output: Option<OutputSpec>,
}

Pre-resolved per-stage setup, applied by enter_stage when an agent enters a stage: inference parameters, tool-result routing, whether the stage accepts live user input, an optional stage-specific context layout, and an optional system prompt. Built once per stage when the agent is spawned (mirrors StageInferences) so stage entry stays synchronous and query-friendly. (Ported from the imperative loop’s per-stage setup in the CLI executor.)

Fields

inference_config: InferenceConfig

Per-stage inference config (temperature / max output tokens).

routing: Option<ToolResultRouting>

Optional per-stage tool-result routing.

accepts_messages: bool

Whether the stage delivers live user messages to the agent.

context_layout: Option<ContextLayout>

Optional stage-specific context layout to swap to on entry.

system_prompt: Option<String>

Optional stage instructions injected as pinned context on entry.

output: Option<OutputSpec>

The output shape resolved for this stage (agent, stage, and the launching caller’s request combined), and whether the stage must produce one. None means no level asked for a shape.

Held here as well as on StageInference because the two use it for different things: this copy is folded into the stage’s system prompt, and that copy is what validates a submission at dispatch.

Trait Implementations

impl Clone for StageSetup

fn clone(&self) -> StageSetup

Returns a duplicate of the value.

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

Performs copy-assignment from source.