Code block evals (#29619)

Add a targeted eval for code block formatting, and revise the system
prompt accordingly.

### Eval before, n=8

<img width="728" alt="eval before"
src="https://github.com/user-attachments/assets/552b6146-3d26-4eaa-86f9-9fc36c0cadf2"
/>

### Eval after prompt change, n=8 (excluding the new evals, so just
testing the prompt change)

<img width="717" alt="eval after"
src="https://github.com/user-attachments/assets/c78c7a54-4c65-470c-b135-8691584cd73e"
/>

Release Notes:

- N/A
This commit is contained in:
Richard Feldman 2025-04-29 18:52:09 -04:00 committed by GitHub
parent 2508e491d5
commit d7004030b3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 536 additions and 134 deletions

View file

@ -12,12 +12,14 @@ use util::serde::default_true;
use crate::example::{Example, ExampleContext, ExampleMetadata, JudgeAssertion};
mod add_arg_to_trait_method;
mod code_block_citations;
mod file_search;
pub fn all(examples_dir: &Path) -> Vec<Rc<dyn Example>> {
let mut threads: Vec<Rc<dyn Example>> = vec![
Rc::new(file_search::FileSearchExample),
Rc::new(add_arg_to_trait_method::AddArgToTraitMethod),
Rc::new(code_block_citations::CodeBlockCitations),
];
for example_path in list_declarative_examples(examples_dir).unwrap() {