eval: Fine-grained assertions (#29246)

- Support programmatic examples
([example](https://github.com/zed-industries/zed/blob/17feb260a0919e102ae4e220669c467885bf4b57/crates/eval/src/examples/file_search.rs))
- Combine data-driven example declarations into a single `.toml` file
([example](https://github.com/zed-industries/zed/blob/17feb260a0919e102ae4e220669c467885bf4b57/crates/eval/src/examples/find_and_replace_diff_card.toml))
- Run judge on individual assertions (previously called "criteria")
- Report judge and programmatic assertions in one combined table

Note: We still need to work on concept naming 

<img width=400
src="https://github.com/user-attachments/assets/fc719c93-467f-412b-8d47-68821bd8a5f5">

Release Notes:

- N/A

---------

Co-authored-by: Richard Feldman <oss@rtfeldman.com>
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Co-authored-by: Thomas Mickley-Doyle <tmickleydoyle@gmail.com>

crates/eval/src/examples/file_search.rs

@@ -0,0 +1,53 @@
+use anyhow::Result;
+use assistant_tools::PathSearchToolInput;
+use async_trait::async_trait;
+use regex::Regex;
+
+use crate::example::{Example, ExampleContext, ExampleMetadata};
+
+pub struct FileSearchExample;
+
+#[async_trait(?Send)]
+impl Example for FileSearchExample {
+    fn meta(&self) -> ExampleMetadata {
+        ExampleMetadata {
+            name: "file_search".to_string(),
+            url: "https://github.com/zed-industries/zed.git".to_string(),
+            revision: "03ecb88fe30794873f191ddb728f597935b3101c".to_string(),
+            language_server: None,
+            max_assertions: Some(4),
+        }
+    }
+
+    async fn conversation(&self, cx: &mut ExampleContext) -> Result<()> {
+        const FILENAME: &str = "find_replace_file_tool.rs";
+        cx.push_user_message(format!(
+                r#"
+        Look at the `{FILENAME}`. I want to implement a card for it. The card should implement the `Render` trait.
+
+        The card should show a diff. It should be a beautifully presented diff. The card "box" should look like what we show for
+        markdown codeblocks (look at `MarkdownElement`). I want to see a red background for lines that were deleted and a green
+        background for lines that were added. We should have a div per diff line.
+        "#
+        ));
+
+        let response = cx.run_turn().await?;
+        let tool_use = response.expect_tool("path_search", cx)?;
+        let input = tool_use.expect_input::<PathSearchToolInput>(cx)?;
+
+        let glob = input.glob;
+        cx.assert(
+            glob.ends_with(FILENAME),
+            format!("glob ends with `{FILENAME}`"),
+        )?;
+
+        let without_filename = glob.replace(FILENAME, "");
+        let matches = Regex::new("(\\*\\*|zed)/(\\*\\*?/)?")
+            .unwrap()
+            .is_match(&without_filename);
+
+        cx.assert(matches, "glob starts with either `**` or `zed`")?;
+
+        Ok(())
+    }
+}