XII · Streaming & UXMature★★

Stop / Cancel

also known as User Interrupt, Abort Generation

Let the user interrupt an in-flight agent run cleanly, releasing resources and surfacing partial state.

Context

A team is running an agent whose individual runs can take tens of seconds to minutes, with multiple tool calls and a streaming response. Halfway through such a run, the user can often see that the agent has misunderstood the request or gone down the wrong path. The team needs a way for the user to stop the run cleanly without closing the tab and without leaving half-written state behind.

Problem

Without a real cancellation path, the user has only bad options: wait for the run to finish, abandon the page (which leaves orphaned tool calls and partial writes in flight), or kill the process and hope nothing important was mid-write. Meanwhile the agent keeps spending tokens, tool calls, and external API quota on work the user already knows is wrong. Implementing a stop button on the user-interface alone is not enough either — the cancellation has to propagate through the agent loop, through each tool call, and into the streaming connection to the model provider, or the run continues invisibly underneath a stopped-looking interface.

Forces

  • Cancellation must reach upstream tools and providers.
  • Partial state may or may not be useful.
  • Race conditions between completion and cancellation.

Example

A user kicks off an agent run that is going off-track within five seconds; right now there is no UI control to stop it and they wait two minutes for completion while cost burns. The team adds a stop control that propagates a cancellation token through the agent loop, tool calls, and provider streams, cleans up partial state, and surfaces what was done. Wrong-direction runs cost seconds rather than minutes and users feel in control.

Diagram

Solution

Therefore:

Surface a stop control in the UI. On click, propagate a cancellation token through the agent loop, tool calls, and provider streams. Clean up partial state. Show what was done. Optionally save partial output for later resumption.

What this pattern forbids. Once cancelled, no further model or tool calls may be issued for the cancelled run.

And the patterns that stand alongside it, or against it —

  • complementsStreaming Typed Events★★— Push partial results to the client as typed events as they become available, rather than waiting for the full response.
  • complementsStep Budget★★— Cap the number of tool calls or loop iterations the agent is allowed within a single request.
  • complementsDecision Paralysis✕— Anti-pattern: when given equally-weighted conflicting goals, the agent either gets stuck trying to satisfy all simultaneously or oscillates between solutions without converging — the most common LLM response to genuine goal conflicts.

Neighbourhood

Click any neighbour to follow the language. Scroll to zoom, drag to pan.

Used in recipes

Used in frameworks

References

Provenance