Struct AgentArguments 

pub struct AgentArguments {
    pub agent_instance_hierarchy: Option<String>,
    pub agent_id: Option<String>,
    pub agent_full_id: Option<String>,
    pub agent_remote: Option<String>,
    pub response_id: Option<String>,
    pub response_ids: Option<String>,
    pub mcp_session_id: Option<String>,
}

Agent identity + response routing args carried per call.

When passed as Some(&AgentArguments) to a [CommandExecutor], subprocess-spawning executors (e.g. [binary::BinaryExecutor]) apply ALL six fields to the spawned child’s env atomically — Some(v) → set, None → env_remove so the parent’s value for that var can’t leak through. None for the whole bag means “inherit parent env unmodified”. In-process executors (e.g. [plugin::PluginExecutor]) ignore the bag.

Field ↔ env-var mapping (same as EnvConfigBuilder in objectiveai-cli/src/run.rs):

• agent_instance_hierarchy ↔ OBJECTIVEAI_AGENT_INSTANCE_HIERARCHY
• agent_id ↔ OBJECTIVEAI_AGENT_ID
• agent_full_id ↔ OBJECTIVEAI_AGENT_FULL_ID
• agent_remote ↔ OBJECTIVEAI_AGENT_REMOTE
• response_id ↔ OBJECTIVEAI_RESPONSE_ID
• response_ids ↔ OBJECTIVEAI_RESPONSE_IDS
• mcp_session_id ↔ MCP_SESSION_ID (the MCP transport session id minted by the MCP server, NOT an objectiveai-scoped identifier — same env-var convention as crate::mcp::MCP_SESSION_ID_ENV)

Fields

agent_instance_hierarchy: Option<String>

agent_id: Option<String>

agent_full_id: Option<String>

agent_remote: Option<String>

response_id: Option<String>

response_ids: Option<String>

mcp_session_id: Option<String>

Implementations

impl AgentArguments

pub fn apply_to_command(&self, command: &mut Command)

Apply this bag to a child-process command: every Some(v) stamps the matching env var, every None env-removes it so the parent’s value can’t leak through. Called by [binary::BinaryExecutor]; available for any executor that spawns a subprocess.

Trait Implementations

impl Clone for AgentArguments

fn clone(&self) -> AgentArguments

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for AgentArguments

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

Formats the value using the given formatter.

impl Default for AgentArguments

fn default() -> AgentArguments

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for AgentArguments

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Eq for AgentArguments

impl JsonSchema for AgentArguments

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 PartialEq for AgentArguments

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

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 AgentArguments