microsoft / microsoft/AI-Engineering-Coach

Error: LLM returned invalid JSON after 3 attempts. Please try again.

Open
#91 0 comments 2 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug
Dominant language
TypeScript
Stars
4.3k
Forks
588
Avg merge
22h 5m
Merged PRs (30d)
16

Description

Description

Hi,
I can't use the AI-driven features like the Skill Finder because I'm getting this error:

Error: LLM returned invalid JSON after 3 attempts. Please try again.

I don't know why I get this error. The copilot chat works fine on its own and I have a Copilot Business subscription.

Steps to Reproduce
  1. Use AI-driven features.
    I used these:
    • Generate Quiz in the Level Up section
    • Play Slop or Not in the Level Up section
    • Analyze in the Skill Finder section
  2. Notice the following error message:
    Error: LLM returned invalid JSON after 3 attempts. Please try again.
    
  3. Try another.
  4. Notice the same error message, but without any loading.
Expected Behavior

IA-Driven features such as Skill Finder work out-of-the-box.
Or
Any extra configuration required (such as API keys) are documented­.

Extension Version

0.1.0 (built from Dev Container using commit e3a5e22bc56bfeccf046ae6a7e90b9f01ecca867)

VS Code Version

1.122.1

Operating System

Windows 11

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the failure in Generate Quiz, Play Slop or Not, and Analyze on the reported extension and VS Code versions, then inspect how these AI-driven features handle the LLM response. Done means the features return valid results reliably, or any required API-key or configuration steps are clearly documented.

Written by the indexing model from the issue text.

Assessment

Tech stack
typescript, vscode
Domain
ai, devtools
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.