LLMs are surprisingly good at reducing crash samples.
I've had success with "this project crashes my static analysis tool with the following command, try to shrink the repro whilst preserving the crash. Commit each smaller version to a branch".
Further tinkering with diagnostics, following feedback!
* Two lines of context above and below now.
* The caret is included in the line below where possible.
* Syntax highlighting of keywords.
I kinda feel that smart context sizing would be better. What do you think so far?
Today I learnt that you can mix HTML inline in markdown! For example, the following is valid.
Foo <hr/>
I'd assumed that you needed HTML separately, like ``` blocks, but no:
https://spec.commonmark.org/0.31.2/#raw-html
Admittedly HTML is very restricted on most sites, but it's helpful for SSGs.