How to Stop, Pause and Continue a Run

By Paul Flanders · · Beginner

Learn how to effectively manage a running request or Plan Mode build using eLLM Code's Stop, Pause, and Continue features. Understand when and why the assistant pauses, and how to guide it to ensure efficient task completion.

Estimated time: 3 minutes
Difficulty: Beginner

Why you'd use this

An agent that can run commands and edit files needs clear brakes. eLLM Code gives you a Stop button that halts everything immediately, and it pauses itself with a stated reason whenever it detects that it is going in circles, so that a stuck model cannot burn through time or gateway credits unattended. Knowing what each pause means lets you decide in seconds whether to push on, steer, or stop.

Before you start

Permissions required:

  • None.

You'll need:

  • A running request or a Plan Mode build in progress.

Steps

  1. While a reply streams, the Send button becomes Stop. Click it to abort the request. Any commands the assistant started, foreground or background, are killed, and no result from them restarts the run.
  2. When the assistant pauses on its own, a note explains why and a bar with Continue and Stop buttons appears above the composer.
  3. Read the reason. The common ones are: it stopped writing code or ticking tasks while tasks remain; it repeated itself without progress; it rewrote the same file repeatedly; it marked tasks done without saving any file; it reached the per-task command limit; or it reached the overall step limit.
  4. Click Continue to send a nudge tailored to that reason. The task list is kept as it is; nothing is marked done that was not.
  5. Instead of Continue, you can type guidance in the composer, for example "The config file is in config/app.json, use that", which resumes the run with your steer.
  6. In a Plan Mode build, typing done tells the assistant the work is finished and skips straight to completion; typing stop halts the plan.
  7. To leave Plan Mode entirely, click Exit on the plan banner at the top of the panel.

What you should see

After Stop, a "Stopped" note confirms nothing else will run until you type a message. After Continue, the run resumes and the pause bar disappears. A command that finishes after you pressed Stop is shown with a "Result held" line and is included with your next message.

Troubleshooting

  • The pause keeps coming back with the same reason: the model is stuck on that task. Open the task list, tell the assistant exactly what to do for the current item, or do that step by hand and say "done with task 3".
  • You pressed Stop but a build is still running in a terminal: only commands started by the assistant are killed. Anything you started yourself is untouched.

Related guides

  • How to Plan and Build a Feature with Plan Mode
  • How to Run Commands from the Chat

person people found this useful.

Related

Knowledge base 11 Sep 2026

How to Send Identity and Intent Headers to the Gateway

Learn how to configure identity and intent headers for a shared gateway using eLLM Code. This guide explains how to adjust settings in VS Code, ensuring requests are routed correctly and usage is attributed accurately.

Knowledge base 11 Sep 2026

How to Tune Generation Settings for Your Model

Learn how to fine-tune generation settings for local and self-hosted models to improve performance and accuracy. Adjust parameters like repetition, prompt size, and command timeouts to better match your model's behaviour.

Knowledge base 11 Sep 2026

How to Run the Benchmark Suite

This article provides a detailed guide on running a benchmark suite to test model configurations, including setup requirements, steps for execution, and troubleshooting tips. It's aimed at advanced users looking to evaluate model capabilities before deployment.

Expand 29 Jul 2026

How AI can support pupils with SEND

Explore how AI tools are aiding pupils with special educational needs and disabilities by simplifying text, breaking down tasks, and enhancing accessibility. Learn about the considerations schools should make before implementation.

Expand 29 Jul 2026

AI policy and practice in further education

Further education colleges need distinct AI policies due to their unique mix of vocational courses, diverse age groups, and specific funding and inspection requirements. This guidance highlights the importance of tailored AI approaches in FE settings.