Introduce LanguageModelToolUse::raw_input (#29322)

This is to enable alternative streaming solutions at the application
layer. I'm not sure we really should have performed parsing of the input
at this layer. Either way I want to experiment with streaming approaches
in a separate crate on a branch, and this will help.

/cc @maxdeviant @bennetbo @rtfeldman

Closes #ISSUE

Release Notes:

- N/A

crates/agent/src/tool_use.rs

@@ -72,6 +72,7 @@ impl ToolUseState {
                             .map(|tool_use| LanguageModelToolUse {
                                 id: tool_use.id.clone(),
                                 name: tool_use.name.clone().into(),
+                                raw_input: tool_use.input.to_string(),
                                 input: tool_use.input.clone(),
                                 is_input_complete: true,
                             })