Overview

A pipeline composes several agents: the developer settles their order and the conditions that move work between them before the run starts, and nothing changes it afterwards. To a caller it looks exactly like one agent, taking inputs and streaming events back. A pipeline takes on three things:

Responsibility	What it means
Fixed logic	Who goes first, what sends work back, how many rounds are allowed: all settled when the pipeline is built, never left to the model
One event stream	Every event from every agent inside leaves through the same `reply_stream`
Human interaction	When an agent stops for tool authorization the pipeline ends the stream instead of suspending, and hands the answer back to whichever agent was waiting

Every agent’s events leave through the same reply_stream. A developer rendering them needs reply_id to tell which agent an event belongs to; it matches that agent’s agent.state.reply_id.

The pipeline module is experimental. Its interfaces may change in later releases.

Interface

PipelineProtocol names one capability: take inputs, stream events.

PipelineProtocol

class PipelineProtocol(Protocol):
    def reply_stream(
        self,
        inputs: Msg
        | list[Msg]
        | UserConfirmResultEvent
        | UserInterruptEvent
        | ExternalExecutionResultEvent,
    ) -> AsyncGenerator[AgentEvent | Msg, None]:
        """Reply to the inputs and stream what happens."""

Agent already satisfies it, an agent being a pipeline of one. So a pipeline goes wherever an agent goes:

Accepting either

async def watch(target: Agent | PipelineProtocol, inputs) -> None:
    # Both are driven the same way, with nothing to branch on
    async for event in target.reply_stream(inputs):
        print(event)

launch_console in the console was widened this way, so a developer can hand a pipeline straight to the terminal.

Implementations

AgentScope ships one pipeline so far:

Class	Arrangement
`GoalPipeline`	An executor produces, a verifier judges, a refusal goes back with its reason, until the work passes or the attempts run out

Goal Pipeline

Keep an executor working until a verifier accepts the result.

Console

Run a pipeline in the terminal and answer its authorization prompts.

Planning

Let the model keep its own task list, which pipelines complement.

Human in the Loop

Authorize tools and resume after an interruption on a single agent.

Get Started

Building Blocks

Agent as Service

Others

Interface

Implementations

Further Reading

Goal Pipeline

Console

Planning

Human in the Loop

​Interface

​Implementations

​Further Reading

Goal Pipeline

Console

Planning

Human in the Loop

Interface

Implementations

Further Reading