Enum Op 

#[non_exhaustive]
pub enum Op {
    Interrupt,
    UserInput {
        items: Vec<InputItem>,
    },
    UserTurn {
        items: Vec<InputItem>,
        cwd: PathBuf,
        approval_policy: AskForApproval,
        sandbox_policy: SandboxPolicy,
        model: String,
        effort: ReasoningEffort,
        summary: ReasoningSummary,
    },
    OverrideTurnContext {
        cwd: Option<PathBuf>,
        approval_policy: Option<AskForApproval>,
        sandbox_policy: Option<SandboxPolicy>,
        model: Option<String>,
        effort: Option<ReasoningEffort>,
        summary: Option<ReasoningSummary>,
    },
    ExecApproval {
        id: String,
        decision: ReviewDecision,
    },
    PatchApproval {
        id: String,
        decision: ReviewDecision,
    },
    AddToHistory {
        text: String,
    },
    GetHistoryEntryRequest {
        offset: usize,
        log_id: u64,
    },
    ListMcpTools,
    Compact,
    Shutdown,
}

Submission operation

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.

Interrupt

Abort current task. This server sends EventMsg::TurnAborted in response.

UserInput

Input from the user

Fields

items: Vec<InputItem>

User input items, see InputItem

UserTurn

Similar to Op::UserInput, but contains additional context required for a turn of a [crate::codex_conversation::CodexConversation].

Fields

items: Vec<InputItem>

User input items, see InputItem

cwd: PathBuf

cwd to use with the SandboxPolicy and potentially tool calls such as local_shell.

approval_policy: AskForApproval

Policy to use for command approval.

sandbox_policy: SandboxPolicy

Policy to use for tool calls such as local_shell.

model: String

Must be a valid model slug for the [crate::client::ModelClient] associated with this conversation.

effort: ReasoningEffort

Will only be honored if the model is configured to use reasoning.

summary: ReasoningSummary

Will only be honored if the model is configured to use reasoning.

OverrideTurnContext

Override parts of the persistent turn context for subsequent turns.

All fields are optional; when omitted, the existing value is preserved. This does not enqueue any input – it only updates defaults used for future UserInput turns.

Fields

cwd: Option<PathBuf>

Updated cwd for sandbox/tool calls.

approval_policy: Option<AskForApproval>

Updated command approval policy.

sandbox_policy: Option<SandboxPolicy>

Updated sandbox policy for tool calls.

model: Option<String>

Updated model slug. When set, the model family is derived automatically.

effort: Option<ReasoningEffort>

Updated reasoning effort (honored only for reasoning-capable models).

summary: Option<ReasoningSummary>

Updated reasoning summary preference (honored only for reasoning-capable models).

ExecApproval

Approve a command execution

Fields

id: String

The id of the submission we are approving

decision: ReviewDecision

The user’s decision in response to the request.

PatchApproval

Approve a code patch

Fields

id: String

The id of the submission we are approving

decision: ReviewDecision

The user’s decision in response to the request.

AddToHistory

Append an entry to the persistent cross-session message history.

Note the entry is not guaranteed to be logged if the user has history disabled, it matches the list of “sensitive” patterns, etc.

Fields

text: String

The message text to be stored.

GetHistoryEntryRequest

Request a single history entry identified by log_id + offset.

Fields

offset: usize

log_id: u64

ListMcpTools

Request the list of MCP tools available across all configured servers. Reply is delivered via EventMsg::McpListToolsResponse.

Compact

Request the agent to summarize the current conversation context. The agent will use its existing context (either conversation history or previous response id) to generate a summary which will be returned as an AgentMessage event.

Shutdown

Request to shut down codex instance.

Trait Implementations

impl Clone for Op

fn clone(&self) -> Op

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Op

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for Op

fn deserialize<__D>( __deserializer: __D, ) -> Result<Op, <__D as Deserializer<'de>>::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for Op

fn eq(&self, other: &Op) -> 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 Op

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for Op