Chat agent is not Format responses for easy readability

[israelcarnahan]

expected responses to return (as they did when last used) in a structured and visually clear manner, such as using markdown, code blocks, or headings. Ensure the content is easy to navigate and comprehend.

current output: now returning in all text format, same colors and hard to read through.

i can get the agent to return a formated response with a prompt ’
Format your responses in a structured and visually clear manner, such as using markdown, code blocks, or headings. Ensure the content is easy to navigate and comprehend." but this is needed to be added to each prompt and not ideal. is there a setting i must have changed? … i am a paid user and am only through less than half of my ‘points’
cant find anything on the line similar.

Windows
auto updates with cursor
issue doesnt stop me from using cursor persay, but causes many more prompts/point usage and take more time, adds more mistakes

Check the forum to ensure the issue hasn’t been reported already
Provide a clear description of the bug
Explain how to reproduce the bug (if known)
Attach screenshots or recordings (e.g., .jpg, .png, .mp4).
Tell us your operating system and your Cursor version (e.g., Windows, 0.x.x).
Tell us if the issue stops you from using Cursor.

[T1000]

Hi, the screenshot shows that your Chat thread was long and that you should start a new thread. In long threads the context is full with a lot of various information and it can cause hallucinations and mistakes by AI as visible in your response.

The only thing that will help is starting a new Chat.

Make sure to plan tasks into a file which you can attach to the next chat and let AI continue where it left of.

Here is an example how this works as posted by another user here in the forum:

[Guide] A Simpler, More Autonomous AI Workflow for Cursor [New Update]

Hey everyone, Following up on the previous KleoSr Cursor Rules system, I’ve been working for the past week and the engagement with the community inside my old thread: [Guide] Maximizing Coding Efficiency with MCP Sequential Thinking & OpenRouter AI - #47 by kleosr the community on my previous thread helped drastically to simplify the approach while aiming for even more autonomy – think closer to a Devin-like experience right within Cursor. From Many Files to Just Two Remember the old system wi…

[deanrie]

Hey, yes, that happens. It’s an old bug that occurs from time to time. We’re working on fixing these issues, but unfortunately, it seems they appear occasionally. Anyway, thank you for the report.