Struct AgentConfig 

pub struct AgentConfig {
    pub name: String,
    pub description: String,
    pub model: String,
    pub reasoning_effort: Option<ReasoningEffort>,
    pub context_window: Option<u32>,
    pub user_invocable: bool,
    pub agent_invocable: bool,
    pub providers: ProviderConnectionOverrides,
    pub prompts: Vec<PromptSource>,
    pub mcps: Vec<McpSourceSpec>,
    pub tools: ToolFilter,
}

A single agent definition. Every agent must be invocable on at least one surface — set userInvocable, agentInvocable, or both.

A user-invocable agent with its own prompt and a tool allowlist:

{
  "name": "Review",
  "description": "Reviews diffs and suggests changes",
  "model": "anthropic:claude-sonnet-4-5-20250929",
  "userInvocable": true,
  "prompts": [".aether/REVIEW.md"],
  "tools": { "allow": ["read_file", "grep", "find"] }
}

A sub-agent (callable by other agents) that pins a Bedrock inference profile:

{
  "name": "Search",
  "description": "Answers questions about the codebase",
  "model": "anthropic.claude-sonnet-4-5-20250929-v1:0",
  "agentInvocable": true,
  "providers": {
    "bedrock": {
      "inferenceProfileArn": "arn:aws:bedrock:us-west-2:000000000000:application-inference-profile/abc"
    }
  }
}

Fields

name: String

Agent identifier. Names are trimmed for merge and lookup.

description: String

Human-readable description shown in UIs and sub-agent listings.

model: String

Model spec for this agent, in provider:model-id form. Accepts a comma-separated alloy of specs to round-robin across turns.

reasoning_effort: Option<ReasoningEffort>

Optional thinking budget for providers that support extended reasoning.

context_window: Option<u32>

Override for the model’s context window, in tokens. Defaults to the model’s advertised window.

user_invocable: bool

Exposes the agent as a user-selectable mode.

agent_invocable: bool

Exposes the agent to the subagents MCP server so other agents can spawn it.

providers: ProviderConnectionOverrides

Per-agent provider overrides, merged over the top-level providers.

prompts: Vec<PromptSource>

Agent-specific prompt sources. A non-empty array replaces the top-level prompts.

mcps: Vec<McpSourceSpec>

Agent-specific MCP sources. A non-empty array replaces the top-level mcps.

tools: ToolFilter

Per-agent MCP tool filter (allow/deny lists).

Trait Implementations

impl Clone for AgentConfig

fn clone(&self) -> AgentConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for AgentConfig

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

Formats the value using the given formatter.

impl Default for AgentConfig

fn default() -> AgentConfig

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for AgentConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl JsonSchema for AgentConfig

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 AgentConfig

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

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 AgentConfig