How to Ask Questions About Your Codebase

By Paul Flanders · · Beginner

Learn how to effectively ask questions about your codebase using eLLM Code in VS Code. This guide covers how to query your project without pasting code, using file references and maintaining context for follow-up questions.

Estimated time: 3 minutes
Difficulty: Beginner

Why you'd use this

When you join a project or return to an unfamiliar area, you want answers grounded in the actual code rather than guesses. eLLM Code reads files, searches the repository and lists folders on its own to answer a question, then cites the files and lines it used. You never paste code into the chat; you ask, and it looks.

Before you start

Permissions required:

  • None. Reading and searching stay inside the open workspace.

You'll need:

  • A project folder open in VS Code with the chat connected.

Steps

  1. Open the chat panel.
  2. Type a question in plain language, for example "How does authentication work in this project?" and press Enter.
  3. Watch the activity lines above the reply. Each shows a tool step: reading a file, searching for a term, or listing a folder.
  4. Read the answer. File references appear as path:line; click one to open that location in the editor.
  5. Ask a follow-up in the same conversation, for example "Where is the token validated?" The assistant keeps the earlier findings in context.
  6. To ask about the file you are editing, click the 📎 Context chip under the composer so the current file or selection is sent with the question. Select a block of code first if you only want that part discussed.

What you should see

A streamed answer with clickable file and line references, preceded by a short list of the files that were read. The status row shows elapsed time, approximate tokens generated and the current conversation size.

Troubleshooting

  • The answer says it could not find something that exists: the search may have hit the step limit. Ask again naming the folder, or raise ellmCode.maxAgentSteps in settings.
  • The conversation grows slow: start a fresh conversation with the button in the header, or run eLLM: Clear Context.
  • Very large files are cut off: file content per request is capped by ellmCode.maxContextBytes. The assistant reads in parts when it needs more.

Related guides

  • How to Use the Command Menu and Composer Toggles
  • How to Use Quick Commands from the Editor
  • How to Check and Manage the Context Window

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.