ViteHub is still experimental. Expect bugs and breaking changes.

Agent Invocations

Understand what ViteHub resolves and records for one Agent request.

An Agent Invocation is one request to run an Agent. It includes the input, trusted caller, selected Capabilities, available context, execution method, and result.

An Agent Definition describes reusable behavior. An Invocation records one execution of that behavior.

What happens during an Invocation

StageWhat happens
EntryA route, Channel, schedule, webhook, CLI command, or another caller provides input.
IdentityViteHub identifies the trusted Agent Invoker and Actor.
CapabilitiesThe Definition and invocation context select the abilities available to this request.
ContextViteHub prepares tools, policy, context values, and Workspace Scope.
ExecutionThe Agent Driver processes the prepared request.
ResultViteHub returns or streams output and records events and usage.

The Agent can use only the Capabilities selected for that Invocation. A Capability that isn't selected contributes nothing to the request.

TermDescribes
Agent DefinitionReusable Agent behavior.
Agent InvocationOne execution for one input.
ChannelMessage origin and delivery facts around an invocation.
Workflow RunDurable work that can continue across waits or server restarts.
Agent MemoryPersistent context stored outside the Invocation.

A Channel can start many Invocations, and a Workflow Run can carry an Invocation. Neither one replaces the request record.

Inspect an invocation

Inspect the input, invoker, Channel, Capabilities, Workspace Scope, Driver, events, usage, and output together. Run vitehub agent info to inspect the Agent definition and vitehub agent dev to stream a local Invocation.

Read Invocations for runAgent() and streamAgent(), or Runtime policy, approvals, and traces for the records produced during execution.