Enum AssistantEvent 

pub enum AssistantEvent {
    ModelServed {
        model_id: String,
        local_last_resort: bool,
    },
    Text(String),
    ToolCall {
        name: String,
        params: Value,
    },
    ToolResult {
        name: String,
        ok: bool,
        content: String,
    },
    Done {
        text: String,
    },
    Error(String),
    GoalEvaluated {
        iteration: u32,
        met: bool,
        grounded: bool,
        reason: String,
    },
}

Streamed events from one loop run. emit is called synchronously as the loop progresses; a chat caller forwards these to agent.chat.event, a CLI caller prints them.

Variants

ModelServed

Attribution for one completed model turn. Emitted before that turn’s text/tool events so every rendered answer can be tied to its actual serving model, including transparent on-device degradation.

Fields

model_id: String

local_last_resort: bool

Text(String)

The model’s free-text for a turn (may be empty when it only calls tools).

ToolCall

A tool is about to run.

Fields

name: String

params: Value

ToolResult

A tool finished. ok is false for a failed/denied call.

Fields

name: String

ok: bool

content: String

Done

Terminal: the model answered with no further tool calls.

Fields

text: String

Error(String)

Terminal: the run failed (inference/transport error).

GoalEvaluated

Goal-loop verifier result after one iteration. This surfaces CAR’s grounded completion evidence to CLI/chat hosts instead of hiding it in tracing logs.

Fields

iteration: u32

met: bool

grounded: bool

reason: String