Enum RunEvent 

#[non_exhaustive]
pub enum RunEvent {
    Started {
        run_id: String,
    },
    Session {
        run_id: String,
        session_id: Option<String>,
        model: Option<String>,
    },
    Text {
        run_id: String,
        delta: String,
    },
    Thinking {
        run_id: String,
        delta: String,
    },
    ToolStart {
        run_id: String,
        tool_call_id: String,
        name: String,
        input: Option<String>,
        tool_kind: ToolKind,
    },
    ToolEnd {
        run_id: String,
        tool_call_id: String,
        ok: bool,
        output: Option<String>,
    },
    SuggestedEdits {
        run_id: String,
        edits: Vec<SuggestedEdit>,
    },
    Activity {
        run_id: String,
        message: String,
    },
    Usage {
        run_id: String,
        input_tokens: Option<u64>,
        output_tokens: Option<u64>,
        total_tokens: Option<u64>,
    },
    AskQuestion {
        run_id: String,
        request_id: String,
        questions: Vec<Question>,
    },
    Error {
        run_id: String,
        message: String,
    },
    Exited {
        run_id: String,
        exit_code: Option<i32>,
        cancelled: bool,
    },
}

The normalized event stream. #[serde(tag = "kind")] + camelCase mirrors the existing ProcessEvent wire contract the TS store already reads (event.kind, event.runId, …), so the front-end consumes one shape regardless of which harness produced it.

Variants (Non-exhaustive)

Non-exhaustive enums could have additional variants added in future. Therefore, when matching against variants of non-exhaustive enums, an extra wildcard arm must be added to account for any future variants.

Started

First event, before any output. UI shows “thinking…”. Fired the instant the process spawns — before the CLI reports its session/model, which arrive separately as RunEvent::Session.

Fields

run_id: String

Session

The agent session is established — its id and the model in use. Distinct from Started because it arrives a beat later, in the CLI’s first output line (bob’s init, Claude’s system/init, codex’s thread.started); keeping Started instant matters for the “thinking…” feedback. Either field may be absent when the CLI doesn’t report it (e.g. codex gives a thread id but no model).

Fields

run_id: String

session_id: Option<String>

model: Option<String>

Text

A chunk of assistant text. Appended to the active message.

Fields

run_id: String

delta: String

Thinking

A chunk of model reasoning (“thinking”), rendered distinctly from Text so the UI can show reasoning without mixing it into the answer (e.g. Claude’s thinking_delta).

Fields

run_id: String

delta: String

ToolStart

A tool call started — render a state-ful card keyed by id. input is the call’s arguments when delivered inline (omitted from the wire when absent, e.g. Claude streams them separately).

Fields

run_id: String

tool_call_id: String

name: String

input: Option<String>

tool_kind: ToolKind

ToolEnd

A tool call finished (matched to its start by id). output is the tool’s result when the harness reports it inline (omitted when absent).

Fields

run_id: String

tool_call_id: String

ok: bool

output: Option<String>

SuggestedEdits

One or more proposed edits. The app prepares + previews them.

Fields

run_id: String

edits: Vec<SuggestedEdit>

Activity

A human-readable status line (tool call, file touch, edit count). Replaces the message’s transient activity text.

Fields

run_id: String

message: String

Usage

Token accounting for the run, emitted near its end (from the CLI’s result / turn.completed). Neutral tokens only — harness-specific costs/credits (bob’s coins) are NOT here; a consumer that wants them reads the harness’s own output. Any field may be absent when the CLI doesn’t break usage down.

Fields

run_id: String

input_tokens: Option<u64>

output_tokens: Option<u64>

total_tokens: Option<u64>

AskQuestion

The agent is asking the user one or more multiple-choice questions (Claude’s AskUserQuestion, Codex’s tool/requestUserInput). The host renders the options as selectable chips; the user’s pick is sent back as their next message on the existing chat path (which resumes the session), so the agent continues with the answer in hand. Carrying the questions as a neutral event keeps the harness-specific tool shape in the adapter — the host never name-checks AskUserQuestion (cf. ToolKind).

Fields

run_id: String

request_id: String

Identifies this question instance (the harness’s tool-call id), so the host can tie the answer + clear the chips for the right one.

questions: Vec<Question>

Error

Spawn / IO / parse failure. Terminal — followed by Exited.

Fields

run_id: String

message: String

Exited

The run finished. Sent exactly once.

Fields

run_id: String

exit_code: Option<i32>

cancelled: bool

Trait Implementations

impl Clone for RunEvent

fn clone(&self) -> RunEvent

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for RunEvent

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

Formats the value using the given formatter.

impl Eq for RunEvent

impl PartialEq for RunEvent

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

Tests for self and other values to be equal, and is used by ==.

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

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for RunEvent

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for RunEvent