Skip to main content

​
ManagedBackendProtocol

Defined in the protocols module.
AI Agent Protocol for external managed agent backends. Defines the contract between PraisonAI Agent’s delegation layer (execution_mixin._delegate_to_backend) and any managed agent infrastructure provider (Anthropic Managed Agents, etc.). The Core SDK defines what — this protocol. The Wrapper implements how — the provider-specific adapter. Lifecycle:: backend = SomeManagedBackend(config={…}) agent = Agent(name=“coder”, backend=backend) result = agent.start(“Write a script”) # delegates to backend.execute() Implementations must handle:
  • Agent/environment/session creation and caching
  • Event streaming (agent.message, agent.tool_use, session.status_idle)
  • Custom tool calls (agent.custom_tool_use → user.custom_tool_result)
  • Tool confirmation (always_ask policy → user.tool_confirmation)
  • Usage tracking (input_tokens, output_tokens)
  • Session reset for multi-turn isolation
Example::

​
Methods

execute()

Execute a prompt on managed infrastructure and return the full response.

stream()

Stream a prompt response as text chunks.

reset_session()

Discard the cached session so the next execute() creates a fresh one.

reset_all()

Discard all cached state (agent, environment, session, client).

update_agent()

Update an existing managed agent’s configuration.

interrupt()

Send a user interrupt to the active session.

retrieve_session()

Retrieve the current managed session’s metadata and usage.

list_sessions()

List sessions for the current agent.

​
Source

View on GitHub

praisonaiagents/agent/protocols.py at line 325