Skip to main content

Module capabilities

Module capabilities 

Source
Expand description

What an agent can do — a categorized snapshot for discovery UIs, routing, and debugging.

Every field is optional and omission means not declared, which is not the same as unsupported. Agents fill in only what they mean to advertise.

Structs§

AgentCapabilities
A typed, categorized snapshot of what an agent supports.
ExecutionCapabilities
Execution controls and limits.
HumanInTheLoopCapabilities
Human-in-the-loop support.
IdentityCapabilities
Agent identity and metadata.
MultiAgentCapabilities
Multi-agent coordination.
MultimodalCapabilities
Multimodal input and output support, split so clients can query each side independently.
MultimodalInputCapabilities
Modalities the agent accepts as input.
MultimodalOutputCapabilities
Modalities the agent can produce.
OutputCapabilities
Output formats the agent can produce.
ReasoningCapabilities
Visibility into the agent’s reasoning.
StateCapabilities
State and memory handling.
SubAgentInfo
A sub-agent a parent agent can invoke.
ToolsCapabilities
Tool-calling support, and the tools the agent brings itself.
TransportCapabilities
Transports the agent speaks.