Hey folks,
Here's a quick tool for anyone who wants a way to simplify error messages with AI without needing to switch to a fully agentic terminal solution. Simply add hank before compiling/running your program to get a clear, readable explanation of any errors that occur.
You can think of this as just another system utility like grep, ls or echo that is at your fingertips for debugging a program. It uses local models as well so your code outputs don't go into online LLM services.
Excited to see what gets thrown back, hope it helps someone. Feel free to add onto it as its pretty raw at the moment.
Looks nice. Would be way more convenient to use if I could just do `?` in the command line after a failed command. I suppose one could create an alias.
Regarding your README, I would add a text version of the example in the demo.
Hey Petar, thanks for checking it out and cool suggestion!
As @alsetmusic already mentioned, I think an alias might be the best way for the moment.
One thing that could be challenging is figuring out how to access the stdout/stderr contents for a program that was previously run. With the current implementation, these pipes are routed to hank although I'm not immediately too sure how one could access this post-execution. Feel free to write or implement any ideas onto the repo!
I believe `?` is considered a reserved word (coming from a Bash background)? I might have that terminology wrong, but I’m remembering `[` (single bracket) as a reserved word that equals `test`, or something close to that. Someone may be able to clarify mistakes in my attempt to get into the details with accuracy regarding terminology.
At the very least, it’s a wildcard. I think you’re not wrong about setting an alias (I have an alias for `??` to link as `$?`, for example). I just think the single character usage will create conflicts and unexpected outcomes.
Cool tool, OP. I’ve marked it to check out when I’m at my computer at home.