-
Notifications
You must be signed in to change notification settings - Fork 237
support AI error suggestion for azd provision
#5521
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Conversation
Azure Dev CLI Install InstructionsInstall scriptsMacOS/Linux
bash:
pwsh:
WindowsPowerShell install
MSI install
Standalone Binary
MSI
Documentationlearn.microsoft.com documentationtitle: Azure Developer CLI reference
|
log.Println("✨ LLM content generation completed") | ||
} | ||
|
||
func promptingWithDifferentErrors(err error) string { |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Instead of dynamically changing the prompt here one suggestion would be to create an MCP tool called something like azd_error_troubleshooting
or something. The response of this error can be a straight forward makrdown document that describes well know types of errors. Each error can provide some troubleshooting advise that the LLM can then use to fix the issue.
The initial prompt can also mention to use this tool to get troubleshooting feedback. Let me know if you have questions.
This change is built on top of @vhvb1989 's implementation on LLM and sampling. After running provision, if there's an error, user will see preview error message and a prompt asking if they want to use their LLM to get AI error suggestion. If they select yes, azd will connect directly to LLM and can sampling response through azd mcp tool (which need to enhance for different commands as next steps and work with #5513) to get AI suggestions.
Next steps:
Example of an azure service error:






If LLM failed to connect:
