Skip to main content

Debugging the Smart Paste UI component

Yesterday I talked about the Smart Paste UI component which should help to automatically fill out a form using data from the user's clipboard. Although the feature worked, the result was weird as an 'of type string' was added to the filled in fields.

Let’s debug the component to understand what is going (wr)on(g).

We start by creating a subclass of type SmartPasteInference:

We register this class in the DI container before the AddSmartComponents():

Add a breakpoint to the BuildPrompt method to inspect the default prompt and parameters. Run the application in debug mode and hit the 'Paste from clipboard button'

Once the breakpoint is hit, we can see the debugger values:

If we drill down in the Messages property, we see the following 2 messages:

That already explains where the ‘of type string’ is coming from. It seems that Llama3 handles these values literally. Let’s try to update the generated prompt to get a better result.

I took the original source code and tweaked it a little bit to omit the type information:

This time our prompt looks like this;

And this is how the result looks like if we paste the following bug description:

I've found a pretty serious issue where the application crashes whenever you try to save your profile. It doesn't matter what browser or operating system you're using, it happens every time. Basically, you just log in, go to the profile page, fill out the form, and hit save. Instead of saving your profile like it should, the whole application crashes and you get this "500 Internal Server Error" message. This is a high priority issue because it prevents users from updating their profiles.


Much better!

Popular posts from this blog

Podman– Command execution failed with exit code 125

After updating WSL on one of the developer machines, Podman failed to work. When we took a look through Podman Desktop, we noticed that Podman had stopped running and returned the following error message: Error: Command execution failed with exit code 125 Here are the steps we tried to fix the issue: We started by running podman info to get some extra details on what could be wrong: >podman info OS: windows/amd64 provider: wsl version: 5.3.1 Cannot connect to Podman. Please verify your connection to the Linux system using `podman system connection list`, or try `podman machine init` and `podman machine start` to manage a new Linux VM Error: unable to connect to Podman socket: failed to connect: dial tcp 127.0.0.1:2655: connectex: No connection could be made because the target machine actively refused it. That makes sense as the podman VM was not running. Let’s check the VM: >podman machine list NAME         ...

Cache stampede: when our cache turned against us

While investigating some performance issues, we ran into an ASP.NET Core API that cached a fairly expensive aggregation query for 60 seconds. Under normal load, that was fine: one request rebuilds the cache, everyone else reads from it. Under peak load, dozens of requests would arrive in that same expiry window, all see a cache miss, and all fire the same expensive query in parallel. The database didn't like that. That was the moment when our caching layer stopped helping and started hurting. A burst of requests comes in at the same time, all miss the cache, and all go hammer the database or the downstream API at once. That's a cache stampede . The cache was supposed to protect our backend, and for a few hundred milliseconds it did the opposite. Why this happens IMemoryCache.GetOrCreate (and its async sibling) looks like it protects you, but it doesn't add any locking on its own. Look at the naive version: public async Task<Report> GetReportAsync(string key) ...

Azure DevOps/ GitHub emoji

I’m really bad at remembering emoji’s. So here is cheat sheet with all emoji’s that can be used in tools that support the github emoji markdown markup: All credits go to rcaviers who created this list.