Struct ToolCallbackContext 

pub struct ToolCallbackContext {
    pub inner: Arc<dyn CallbackContext>,
    pub tool_name: String,
    pub tool_input: Value,
}

Core traits and types.

Always available regardless of feature flags. Includes:

• Agent - The fundamental trait for all agents
• Tool / Toolset - For extending agents with capabilities
• Session / State - For managing conversation context
• Event - For streaming agent responses
• AdkError / Result - Unified error handling Wraps a CallbackContext to inject tool name and input for before-tool and after-tool callbacks.

Used by the agent runtime to provide tool context to BeforeToolCallback and AfterToolCallback invocations.

Example

let tool_ctx = Arc::new(ToolCallbackContext::new(
    ctx.clone(),
    "search".to_string(),
    serde_json::json!({"query": "hello"}),
));
callback(tool_ctx as Arc<dyn CallbackContext>).await;

Fields

inner: Arc<dyn CallbackContext>

The inner callback context to delegate to.

tool_name: String

The name of the tool being executed.

tool_input: Value

The input arguments for the tool being executed.

Implementations

impl ToolCallbackContext

pub fn new( inner: Arc<dyn CallbackContext>, tool_name: String, tool_input: Value, ) -> ToolCallbackContext

Creates a new ToolCallbackContext wrapping the given inner context.

Trait Implementations

impl CallbackContext for ToolCallbackContext

fn artifacts(&self) -> Option<Arc<dyn Artifacts>>

fn tool_outcome(&self) -> Option<ToolOutcome>

Returns structured metadata about the most recent tool execution. Available in after-tool callbacks and plugin hooks. Returns None when not in a tool execution context.

fn tool_name(&self) -> Option<&str>

Returns the name of the tool about to be executed. Available in before-tool and after-tool callback contexts.

fn tool_input(&self) -> Option<&Value>

Returns the input arguments for the tool about to be executed. Available in before-tool and after-tool callback contexts.

fn shared_state(&self) -> Option<Arc<SharedState>>

Returns the shared state for parallel agent coordination. Returns None when not running inside a ParallelAgent with shared state enabled.

impl ReadonlyContext for ToolCallbackContext

fn invocation_id(&self) -> &str

fn agent_name(&self) -> &str

fn user_id(&self) -> &str

fn app_name(&self) -> &str

fn session_id(&self) -> &str

fn branch(&self) -> &str

fn user_content(&self) -> &Content

fn try_app_name(&self) -> Result<AppName, AdkError>

Returns the application name as a typed AppName.

fn try_user_id(&self) -> Result<UserId, AdkError>

Returns the user identifier as a typed UserId.

fn try_session_id(&self) -> Result<SessionId, AdkError>

Returns the session identifier as a typed SessionId.

fn try_invocation_id(&self) -> Result<InvocationId, AdkError>

Returns the invocation identifier as a typed InvocationId.

fn try_identity(&self) -> Result<AdkIdentity, AdkError>

Returns the stable session-scoped AdkIdentity triple.

fn try_execution_identity(&self) -> Result<ExecutionIdentity, AdkError>

Returns the full per-invocation ExecutionIdentity.