agent: Handle attempts to use hallucinated tools (#29946)

This change:

1. Catches attempts to use missing tools. If this happens, we now send
Agent a message listing available tools, after which Agent can
gracefully recover. Prior behavior: thread would stop in a broken state.

Example of a hallucinated call and a message we send back: 

![image](https://github.com/user-attachments/assets/92a8f700-b192-4038-8c7e-0a74ca2e0146)

2. Adds evals for hallucinated tool use and imagined edits
3. Adds ability to configure a profile name in evals.



Release Notes:

- N/A

crates/eval/src/examples/planets.rs

@@ -1,4 +1,5 @@
 use anyhow::Result;
+use assistant_settings::AgentProfileId;
 use assistant_tool::Tool;
 use assistant_tools::{OpenTool, TerminalTool};
 use async_trait::async_trait;
@@ -16,6 +17,7 @@ impl Example for Planets {
             revision: "59e49c75214f60b4dc4a45092292061c8c26ce27".to_string(), // so effectively a blank project.
             language_server: None,
             max_assertions: None,
+            profile_id: AgentProfileId::default(),
         }
     }